© 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. 2822
    Prev
    Next
    INDEX
    Explanations

    ska band names

    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
     tob
    -0.11
     Rap
    -0.11
    Handler
    -0.10
    ä¾
    -0.10
     Antique
    -0.09
     Freem
    -0.09
     Miche
    -0.09
    omaly
    -0.09
    aporation
    -0.09
     jaz
    -0.09
    POSITIVE LOGITS
     punk
    0.20
    punk
    0.19
     garage
    0.17
    æľĭ
    0.17
     Punk
    0.16
     DIY
    0.15
     bands
    0.14
     Reagan
    0.13
     Thatcher
    0.13
     oi
    0.13
    Activations Density 0.046%

    No Known Activations