© 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. 56541
    Prev
    Next
    INDEX
    Explanations

    auto- related terms

    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
     wound
    -0.10
    .ws
    -0.10
     pneumonia
    -0.10
     dementia
    -0.10
     grosse
    -0.10
     Kens
    -0.09
    stringstream
    -0.09
    Bars
    -0.09
     Sas
    -0.09
     Gross
    -0.09
    POSITIVE LOGITS
     Auto
    0.31
    Auto
    0.28
     auto
    0.28
    auto
    0.26
     autoimmune
    0.26
    -auto
    0.23
     AUTO
    0.22
    /auto
    0.21
    .Auto
    0.21
    (auto
    0.21
    Activations Density 0.025%

    No Known Activations