© 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. 56058
    Prev
    Next
    INDEX
    Explanations

    much

    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
     Extremely
    -0.12
     slightly
    -0.12
    çķ¥
    -0.10
     slight
    -0.10
    ç¨į
    -0.10
    :::::::::::::
    -0.09
     unprecedented
    -0.09
     fairly
    -0.09
    ako
    -0.09
     several
    -0.09
    POSITIVE LOGITS
     much
    0.32
     very
    0.23
    much
    0.23
     veel
    0.21
     muito
    0.21
    å¾Ī
    0.20
     too
    0.20
     molto
    0.20
     mycket
    0.20
     çok
    0.18
    Activations Density 0.098%

    No Known Activations