© 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. 33304
    Prev
    Next
    INDEX
    Explanations

    not perfect, incomplete, partial

    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
     flat
    -0.11
    igor
    -0.10
    æĹł
    -0.10
     ÑģовеÑĢÑĪенно
    -0.09
     entirely
    -0.09
    毫
    -0.09
    flat
    -0.09
    bih
    -0.09
    -flat
    -0.09
    หมà¸Ķ
    -0.09
    POSITIVE LOGITS
     partial
    0.41
     Partial
    0.34
    Partial
    0.33
    partial
    0.31
     incomplete
    0.31
     partially
    0.30
    Incomplete
    0.29
    .partial
    0.28
    _partial
    0.28
     imperfect
    0.26
    Activations Density 0.217%

    No Known Activations