© 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. 40009
    Prev
    Next
    INDEX
    Explanations

    forbidden or harmful actions

    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
    uet
    -0.10
    outu
    -0.09
    kes
    -0.08
    tract
    -0.08
     prot
    -0.08
    descricao
    -0.08
    èĩ³å°ij
    -0.08
    801
    -0.08
    ì²ł
    -0.08
    anners
    -0.08
    POSITIVE LOGITS
     any
    0.21
    ä»»ä½ķ
    0.20
     ANY
    0.20
     such
    0.17
     anything
    0.16
    any
    0.16
     or
    0.15
     anyone
    0.14
    such
    0.14
    anything
    0.14
    Activations Density 0.132%

    No Known Activations