Execution attempt · A79 · planned
Runs the teacher-forced logit lens of Bielik-PL-11B-v3.0-Instruct over its 1,600 Polish and English chain-of-thought traces.
Pinned source and configuration
https://github.com/stw2/tokenizer-science-tax @ 6a20c5c41c509137b0de80a80ec4fd3d3243ba56
Reference checked 2026-09-14 13:12 UTC. Later commits, branches or plan changes do not retarget this attempt.
- Command
- python scripts/02_lens_run.py
- Working directory
- experiments/E08-latent-pivot
- Configuration paths
- None
- Parameters
- model bielik-pl-11b-v3.0-instruct; conditions pl and en; layers 1 to 50; reasoning positions before the first answer marker; the default command runs both models in order
- Environment
- 3.12.13; Apple MLX (Metal), bf16 weights, custom loop over 50 blocks without KV cache, fp32 softmax; Apple silicon, 128 GB unified memory
- Output directory
- Not recorded
Inputs
Materials the registrant named when registering this attempt, by content identity; obtainability is derived from their location reports. Nothing is fetched or verified.
- model repository bielik-pl-11b-v3.0-instruct · model · M46 Bielik-PL-11B-v3.0-Instruct · model · Ask the reporter
- bielik-pl-11b-v3.0-instruct mlx-bf16 · checkpoint · M65 bielik-pl-11b-v3.0-instruct mlx-bf16 · raw output · Ask the reporter
- traces bielik-pl-11b-v3.0-instruct · evaluation data · M99 raw/run_bielik-pl-11b-v3.0-instruct.jsonl · raw output · Ask the reporter
- lexicon_bielik-pl-11b-v3.0-instruct.json · vocabulary partition · M398 lexicon_bielik-pl-11b-v3.0-instruct.json · raw output · Download
- prompt builder 02_run.py · prompt builder · M396 Prompt builder of the reasoning-language runs, version run with the lens · code · No known location
- e3_config.json · configuration · M397 Configuration of the reasoning-language runs · configuration · Download
- item manifest · configuration · M96 manifest.json · raw output · Download
- exemplars · evaluation data · M95 exemplars.json · raw output · Ask the reporter
- items gsm8k-pl · evaluation data · M92 items_gsm8k_pl.jsonl · raw output · Download
- items llmzszl-stem · evaluation data · M93 items_llmzszl_stem.jsonl · raw output · Ask the reporter
- items pes · evaluation data · M94 items_pes.jsonl · raw output · Ask the reporter
Delivered events
Registered
#1Runs the teacher-forced logit lens of Bielik-PL-11B-v3.0-Instruct over its 1,600 Polish and English chain-of-thought traces.
Started
#2Started.
Succeeded
#3Completed with exit code 0.
Exit code 0.
- lens_bielik-pl-11b-v3.0-instruct.jsonl · https://github.com/stw2/tokenizer-science-tax/blob/a9246a60690bf1627e4cc56095f64e3307508bb2/experiments/E08-latent-pivot/results/raw/lens_bielik-pl-11b-v3.0-instruct.jsonl · public · sha256 4c486291da83… · 7101513 bytes · M405
- low_agree_bielik-pl-11b-v3.0-instruct.json · https://github.com/stw2/tokenizer-science-tax/blob/a9246a60690bf1627e4cc56095f64e3307508bb2/experiments/E08-latent-pivot/results/low_agree_bielik-pl-11b-v3.0-instruct.json · public · sha256 58c7575c1b1d… · 36146 bytes · M406
Report an event
The registrant’s capture tool normally delivers start and outcome events. Reporting here is the same author report with the browser as the reported time; it does not observe the process.
This attempt has a delivered outcome. A new execution is a new attempt.