© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 52395
    Prev
    Next
    INDEX
    Explanations

    negative outcomes and severe harm

    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
    idor
    -0.09
    ¶Į
    -0.09
     Dunk
    -0.09
     tear
    -0.09
     Nack
    -0.08
    usat
    -0.08
     Sik
    -0.08
    .chk
    -0.08
    ypes
    -0.08
     Mayer
    -0.08
    POSITIVE LOGITS
    -like
    0.17
     risk
    0.14
     if
    0.12
     or
    0.12
    -esque
    0.11
    -level
    0.11
    é£İéĻ©
    0.11
     unless
    0.10
    -worthy
    0.10
     nếu
    0.10
    Activations Density 0.093%

    No Known Activations