© 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. 13638
    Prev
    Next
    INDEX
    Explanations

    directions and movement

    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
     west
    -0.13
     east
    -0.12
     north
    -0.12
    olds
    -0.09
     south
    -0.09
    edd
    -0.09
     Haram
    -0.09
     EAST
    -0.09
    643
    -0.09
     Tanner
    -0.09
    POSITIVE LOGITS
    wards
    0.31
    ward
    0.30
    WARDS
    0.18
     wards
    0.18
    /up
    0.17
    WARD
    0.17
    owards
    0.16
    ards
    0.15
    /down
    0.15
    warts
    0.15
    Activations Density 0.071%

    No Known Activations