© 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. 25509
    Prev
    Next
    INDEX
    Explanations

    a simple implementation

    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
    aras
    -0.11
    ocommerce
    -0.10
    oland
    -0.09
     Gaw
    -0.09
    ::::/
    -0.09
    atoire
    -0.09
     Daw
    -0.09
     Hag
    -0.09
     JMP
    -0.08
     incapac
    -0.08
    POSITIVE LOGITS
     implementation
    0.26
     implementations
    0.23
     Implementation
    0.21
     implement
    0.20
    implementation
    0.19
     impl
    0.19
    Implementation
    0.19
     Implement
    0.18
     implementing
    0.18
     implemented
    0.17
    Activations Density 0.202%

    No Known Activations