© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 32557
    Prev
    Next
    INDEX
    Explanations

    PLANNING TASK STRUCTURE

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Apost
    -0.10
     Tob
    -0.10
     cane
    -0.09
    éŀĭ
    -0.09
     Grade
    -0.09
    oki
    -0.09
    -gnu
    -0.09
     purpose
    -0.09
    ZA
    -0.09
     el
    -0.08
    POSITIVE LOGITS
    KB
    0.13
     goal
    0.12
     KB
    0.12
    ddl
    0.10
    _goal
    0.10
     planning
    0.10
     Goal
    0.10
    goal
    0.10
     Planning
    0.10
     strips
    0.10
    Activations Density 0.063%

    No Known Activations