© 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. 62178
    Prev
    Next
    INDEX
    Explanations

    pale skin or baleen

    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
    re
    -0.14
    res
    -0.13
    n
    -0.13
    rel
    -0.12
    red
    -0.12
    r
    -0.11
    ro
    -0.11
    ra
    -0.11
    dan
    -0.11
    d
    -0.11
    POSITIVE LOGITS
    idos
    0.19
    stinian
    0.15
    mb
    0.15
    olithic
    0.14
    volent
    0.12
    NDAR
    0.12
    igh
    0.12
    aÄŁ
    0.12
    ontology
    0.12
    st
    0.12
    Activations Density 0.055%

    No Known Activations