© 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. 44432
    Prev
    Next
    INDEX
    Explanations

    damage and repair

    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
     Ritch
    -0.09
    akening
    -0.09
    опÑĢоÑģ
    -0.09
     Downs
    -0.09
    298
    -0.09
    fec
    -0.09
     grit
    -0.09
    gom
    -0.09
     Relief
    -0.08
    cke
    -0.08
    POSITIVE LOGITS
     wounds
    0.27
     broken
    0.22
     wound
    0.17
    broken
    0.17
     wounded
    0.17
     damage
    0.17
     injuries
    0.16
     vết
    0.16
     damaged
    0.16
     Broken
    0.16
    Activations Density 0.060%

    No Known Activations