© 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 (Instruct)
    5. 50-RESID-POST-GF
    7. 33988
    Prev
    Next
    INDEX
    Explanations

    majority, minority, largest

    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
    illo
    -0.11
     Mant
    -0.09
     Sung
    -0.09
    illas
    -0.09
     Yus
    -0.09
    illa
    -0.08
    urv
    -0.08
    rend
    -0.08
     Ast
    -0.08
    arend
    -0.08
    POSITIVE LOGITS
     minority
    0.68
     Minority
    0.51
     minorities
    0.48
     majority
    0.42
    minor
    0.38
    Minor
    0.36
     Majority
    0.35
     mayorÃŃa
    0.31
     thiá»ĥu
    0.30
     minor
    0.29
    Activations Density 0.043%

    No Known Activations