© 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. 52057
    Prev
    Next
    INDEX
    Explanations

    words starting with m

    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
    ais
    -0.14
    ap
    -0.13
    utex
    -0.13
    agento
    -0.13
    ax
    -0.13
    ask
    -0.12
    sg
    -0.12
    bps
    -0.12
    ozilla
    -0.12
    any
    -0.11
    POSITIVE LOGITS
    ep
    0.15
    olar
    0.14
    roe
    0.14
    ow
    0.14
    ew
    0.13
     ost
    0.13
    oping
    0.13
    caff
    0.13
    anger
    0.12
     eas
    0.12
    Activations Density 0.118%

    No Known Activations