© 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. 32370
    Prev
    Next
    INDEX
    Explanations

    information obtained from

    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
    Processed
    -0.11
    740
    -0.10
    chez
    -0.10
    gone
    -0.10
    processed
    -0.09
     Gone
    -0.09
    -born
    -0.09
     gone
    -0.09
     garner
    -0.09
     processed
    -0.09
    POSITIVE LOGITS
    æĿ¥èĩª
    0.32
     obtained
    0.31
     from
    0.24
     taken
    0.22
     obten
    0.21
     Obt
    0.20
     obtain
    0.20
     pulled
    0.19
    à¸Īาà¸ģ
    0.18
     zÃŃsk
    0.18
    Activations Density 0.354%

    No Known Activations