© 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. 27956
    Prev
    Next
    INDEX
    Explanations

    question words following clauses

    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
     Sort
    -0.14
    .Formatter
    -0.12
    Sort
    -0.10
    ÂĢÂĢ
    -0.09
     sort
    -0.08
    éĢļãĤĬ
    -0.08
    ãģłãģ£ãģ¦
    -0.08
    hin
    -0.08
    ¶Į
    -0.08
    atra
    -0.07
    POSITIVE LOGITS
     how
    0.25
     what
    0.24
    what
    0.20
     How
    0.19
     What
    0.19
    how
    0.18
    How
    0.18
    å¦Ĥä½ķ
    0.17
    What
    0.17
    ä»Ģä¹Ī
    0.16
    Activations Density 0.264%

    No Known Activations