© 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. 34412
    Prev
    Next
    INDEX
    Explanations

    conversation turn markers

    np_acts-logits-general · gemini-2.5-flash-lite

    markers signaling chat metadata and structure, such as message headers, role tags, and conversation boundary tokens.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    998
    -0.08
    ujet
    -0.08
    ecure
    -0.08
     öt
    -0.08
    ulton
    -0.08
     Moo
    -0.08
    290
    -0.07
    afari
    -0.07
     Placeholder
    -0.07
    reet
    -0.07
    POSITIVE LOGITS
     actually
    0.08
     ÑĤабли
    0.08
    (æľ¨
    0.08
     zwar
    0.08
    оÑĢаÑı
    0.08
    setQuery
    0.08
    ellite
    0.08
    ,},\n
    0.08
    aley
    0.08
     actual
    0.08
    Activations Density 0.454%

    No Known Activations