© 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. 62145
    Prev
    Next
    INDEX
    Explanations

    illegal and

    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
     Pistol
    -0.09
     foul
    -0.09
    й
    -0.09
    axe
    -0.09
    _ASSUME
    -0.09
     ax
    -0.08
    æĢ¥
    -0.08
    ãİ
    -0.08
    ertools
    -0.08
    gaard
    -0.08
    POSITIVE LOGITS
    StateException
    0.18
    ities
    0.17
    /legal
    0.15
    ised
    0.12
    ized
    0.12
    /il
    0.11
     anywhere
    0.11
    istic
    0.11
    idade
    0.10
     according
    0.10
    Activations Density 0.021%

    No Known Activations