© 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. 54896
    Prev
    Next
    INDEX
    Explanations

    risk of harm or damage

    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¸Ģç§į
    -0.14
    ä¸ĢäºĽ
    -0.11
    ä¸ĢåĢĭ
    -0.10
    672
    -0.10
    ä¸ĢåĪĩ
    -0.10
    ä¸Ģ
    -0.09
    plib
    -0.09
     unfore
    -0.09
     attempt
    -0.08
    oeff
    -0.08
    POSITIVE LOGITS
     injury
    0.14
     harm
    0.12
     serious
    0.11
     becoming
    0.10
    error
    0.10
     infection
    0.10
     developing
    0.09
    verse
    0.09
    334
    0.09
     success
    0.09
    Activations Density 0.033%

    No Known Activations