© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 1992
    Prev
    Next
    INDEX
    Explanations

    top of

    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
    -sided
    -0.11
     tops
    -0.11
     sided
    -0.10
    isle
    -0.09
     Marketable
    -0.09
    ulp
    -0.08
    teg
    -0.08
    аÑĢÑĮ
    -0.08
    naire
    -0.08
     doorway
    -0.08
    POSITIVE LOGITS
     part
    0.21
     portion
    0.20
     of
    0.19
     end
    0.15
     edge
    0.14
    most
    0.14
     ÑĩаÑģÑĤÑĮ
    0.13
     của
    0.13
    éĥ¨åĪĨ
    0.12
    éĥ¨
    0.12
    Activations Density 0.083%

    No Known Activations