© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 37903
    Prev
    Next
    INDEX
    Explanations

    fractal or fraction

    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
    ahan
    -0.10
    rame
    -0.10
    ificio
    -0.10
    beros
    -0.09
    erness
    -0.09
    ãĤ¡
    -0.09
    /false
    -0.09
    ût
    -0.09
     refin
    -0.09
    æ½®
    -0.09
    POSITIVE LOGITS
    ernal
    0.14
     Fr
    0.13
    /fr
    0.13
    (fr
    0.13
    -fr
    0.12
    furt
    0.12
    .parseFloat
    0.12
    al
    0.11
    ulent
    0.11
    fur
    0.11
    Activations Density 0.044%

    No Known Activations