© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 38752
    Prev
    Next
    INDEX
    Explanations

    broken down intobroken down into simplerbeing transported into generate significant

    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
    tc
    -0.09
    :::::::::
    -0.09
    ISTORY
    -0.09
    obe
    -0.08
    otec
    -0.08
     Glover
    -0.08
    ihan
    -0.08
    arrera
    -0.08
     Commod
    -0.08
    .Footer
    -0.08
    POSITIVE LOGITS
    kiye
    0.10
    atron
    0.09
     Những
    0.09
    #
    0.09
    antz
    0.09
     những
    0.08
     Tus
    0.08
    allee
    0.08
     those
    0.08
    cura
    0.08
    Activations Density 0.300%

    No Known Activations