© 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. 13532
    Prev
    Next
    INDEX
    Explanations

    affected by, related to, levels 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
     ë¥
    -0.08
    zw
    -0.08
     bz
    -0.08
    _chan
    -0.08
     relu
    -0.08
    ëł¹
    -0.08
    Trivia
    -0.07
    NÄ°
    -0.07
    åĴ²
    -0.07
    ETO
    -0.07
    POSITIVE LOGITS
     olmayan
    0.08
    yleft
    0.08
    .protobuf
    0.08
     //~
    0.08
    gp
    0.08
    æĭ©
    0.07
     COPYRIGHT
    0.07
     [](
    0.07
    ics
    0.07
    Laugh
    0.07
    Activations Density 0.022%

    No Known Activations