© 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. 59534
    Prev
    Next
    INDEX
    Explanations

    click triggers action

    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
    _hover
    -0.09
    hover
    -0.09
    ardon
    -0.09
    arta
    -0.09
    alat
    -0.08
    .itemView
    -0.08
     Hoff
    -0.08
    ãĥ³ãĥIJãĥ¼
    -0.08
    enser
    -0.08
     buttons
    -0.08
    POSITIVE LOGITS
     trigger
    0.17
     fires
    0.15
     calls
    0.14
     Fires
    0.13
     triggers
    0.13
     call
    0.12
    iggers
    0.12
     action
    0.12
    trigger
    0.12
     Fired
    0.11
    Activations Density 0.070%

    No Known Activations