© 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. 34403
    Prev
    Next
    INDEX
    Explanations

    dangerous and its derivations

    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
    152
    -0.09
    TING
    -0.09
     Lazar
    -0.09
    azar
    -0.09
    ting
    -0.09
    zilla
    -0.09
     endings
    -0.08
     Gow
    -0.08
    727
    -0.08
    sy
    -0.08
    POSITIVE LOGITS
    ous
    0.29
    ously
    0.26
    éĻº
    0.17
    éļª
    0.15
    oust
    0.14
    éĻ©
    0.14
    -danger
    0.12
    ouse
    0.12
    osity
    0.11
    OUS
    0.11
    Activations Density 0.021%

    No Known Activations