© 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. 62308
    Prev
    Next
    INDEX
    Explanations

    coherence, consistency, clarity, efficiency

    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
    lest
    -0.10
    loh
    -0.10
    æ¦
    -0.10
     èĻ
    -0.09
    owitz
    -0.09
     generic
    -0.09
    ANJI
    -0.09
     nik
    -0.09
    -generic
    -0.09
    weeney
    -0.09
    POSITIVE LOGITS
    à¹ĥà¸Ļà¸ģาร
    0.14
     regarding
    0.12
     between
    0.11
     surrounding
    0.10
    hibited
    0.10
     Crescent
    0.09
    /documentation
    0.09
     across
    0.09
     Workspace
    0.09
    ality
    0.09
    Activations Density 0.079%

    No Known Activations