© 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. 34336
    Prev
    Next
    INDEX
    Explanations

    possible for someone to

    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
    ãģĭãģij
    -0.11
     reco
    -0.11
    ä¸įåĪ°
    -0.10
    .eql
    -0.10
    -gnu
    -0.10
    acom
    -0.09
    appe
    -0.09
    ãģıãģł
    -0.09
    acent
    -0.09
    681
    -0.09
    POSITIVE LOGITS
     be
    0.17
    /from
    0.17
     whom
    0.17
    iling
    0.14
    gether
    0.14
    /of
    0.11
    ying
    0.11
    pper
    0.11
    ffee
    0.10
    cken
    0.10
    Activations Density 0.080%

    No Known Activations