© 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. 13476
    Prev
    Next
    INDEX
    Explanations

    opening try or half

    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
     goalkeeper
    -0.12
     Goals
    -0.10
    Goals
    -0.10
     ker
    -0.10
     ranger
    -0.10
     Portland
    -0.10
     Gol
    -0.09
     Dwight
    -0.09
     Rangers
    -0.09
    -INF
    -0.09
    POSITIVE LOGITS
    rug
    0.19
     scr
    0.18
     prop
    0.18
     rugby
    0.18
     Rugby
    0.15
     props
    0.15
     Samoa
    0.15
     hookers
    0.15
     XV
    0.14
     rug
    0.14
    Activations Density 0.007%

    No Known Activations