© 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. 21694
    Prev
    Next
    INDEX
    Explanations

    interracial murders, skin thickness, years practicing

    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
     )\n\n\n\n\n\n\n\n
    -0.09
     dbg
    -0.09
     hammer
    -0.09
     Daw
    -0.08
     Chapman
    -0.08
    RIES
    -0.08
     helper
    -0.08
     Invent
    -0.08
    _lens
    -0.08
     Binder
    -0.08
    POSITIVE LOGITS
     Crow
    0.11
     Assault
    0.10
    ån
    0.09
    qrt
    0.09
     crow
    0.09
    HITE
    0.09
     intercept
    0.09
    اÙĦس
    0.08
    <?\n
    0.08
     Lyon
    0.08
    Activations Density 0.017%

    No Known Activations