© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 13347
    Prev
    Next
    INDEX
    Explanations

    statistical analysis

    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
    ãģĬãĤĬ
    -0.14
    AMS
    -0.09
    Wunused
    -0.09
    ãģĦãģ¾ãģĻ
    -0.09
    ITAL
    -0.09
    din
    -0.09
     instruct
    -0.08
    elt
    -0.08
    864
    -0.08
     strokes
    -0.08
    POSITIVE LOGITS
    istical
    0.17
     significance
    0.16
    /stat
    0.14
    /math
    0.12
    istically
    0.12
     significant
    0.12
     Significant
    0.11
    (stat
    0.11
     quo
    0.11
     analysis
    0.11
    Activations Density 0.008%

    No Known Activations