© 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. 56934
    Prev
    Next
    INDEX
    Explanations

    In terms of

    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
    295
    -0.10
    è¥
    -0.09
    ucer
    -0.09
    iquer
    -0.09
    太éĥİ
    -0.09
    odox
    -0.08
    ember
    -0.08
    ypes
    -0.08
    ç¼
    -0.08
    venge
    -0.08
    POSITIVE LOGITS
     terms
    0.82
    terms
    0.61
     Terms
    0.59
    Terms
    0.55
     TERMS
    0.49
    _terms
    0.45
    /terms
    0.37
     tér
    0.34
     term
    0.32
     terme
    0.29
    Activations Density 0.042%

    No Known Activations