© 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. 63525
    Prev
    Next
    INDEX
    Explanations

    as something

    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
     evidenced
    -0.14
     evid
    -0.11
    tha
    -0.09
    the
    -0.09
    arie
    -0.09
    elik
    -0.09
    mek
    -0.09
     æĵ
    -0.09
    ungan
    -0.09
    ideographic
    -0.09
    POSITIVE LOGITS
     follows
    0.25
    -is
    0.21
     soon
    0.17
     part
    0.14
     though
    0.14
    ynch
    0.14
     usual
    0.13
    lant
    0.13
    ap
    0.13
    ynchron
    0.13
    Activations Density 0.074%

    No Known Activations