© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 56139
    Prev
    Next
    INDEX
    Explanations

    and organizations

    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
     genre
    -0.13
     genres
    -0.12
    genres
    -0.11
    ohan
    -0.10
    Genres
    -0.10
    aga
    -0.10
     sectors
    -0.10
    andom
    -0.10
     themed
    -0.10
     domains
    -0.10
    POSITIVE LOGITS
     corresponding
    0.11
     sub
    0.10
     subdivisions
    0.09
    $MESS
    0.09
    à¹Ģà¸ģษ
    0.09
     subdiv
    0.09
    aska
    0.09
    imson
    0.09
    lyph
    0.09
    ãĢĤwww
    0.09
    Activations Density 0.140%

    No Known Activations