© 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. 37902
    Prev
    Next
    INDEX
    Explanations

    request prompts

    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
     Redemption
    -0.10
    ç½²
    -0.09
    osen
    -0.09
    473
    -0.09
    ï¼¹
    -0.09
     Netflix
    -0.09
    Netflix
    -0.08
    163
    -0.08
    Surname
    -0.08
     Airbnb
    -0.08
    POSITIVE LOGITS
    untime
    0.10
    ehir
    0.10
    achuset
    0.09
    olik
    0.09
     Lob
    0.09
    hcp
    0.08
     Blender
    0.08
    ttp
    0.08
    isÃŃ
    0.08
    tet
    0.08
    Activations Density 0.018%

    No Known Activations