© 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. 27511
    Prev
    Next
    INDEX
    Explanations

    potential negative consequences

    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
    ä¸īä¸ī
    -0.09
     Unsafe
    -0.09
     Impossible
    -0.09
    kul
    -0.09
    adaÅŁ
    -0.09
    mÃŃt
    -0.08
    æĻ´
    -0.08
    ERO
    -0.08
    ange
    -0.08
    ROUGH
    -0.08
    POSITIVE LOGITS
     danger
    0.27
     risk
    0.24
     worry
    0.23
     risks
    0.20
     possibility
    0.19
     خطر
    0.19
     Danger
    0.19
     worries
    0.18
     concern
    0.17
     potentially
    0.17
    Activations Density 0.086%

    No Known Activations