© 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. 37162
    Prev
    Next
    INDEX
    Explanations

    code or technical terms

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

    short, common English words used as standalone tokens, often technical or functional terms in text or code contexts.

    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
    /Dk
    -0.10
    (ARG
    -0.09
    ÂĢÂĢ
    -0.09
    etÃŃ
    -0.08
    nemonic
    -0.08
     seksi
    -0.08
    ｧ
    -0.08
    \Dependency
    -0.08
    µľ
    -0.08
    اطÙĦ
    -0.08
    POSITIVE LOGITS
    \-
    0.10
    ;amp
    0.08
     sod
    0.08
    uito
    0.08
     Prest
    0.08
     Tir
    0.08
     Pap
    0.08
    eward
    0.08
     pa
    0.08
     AMS
    0.07
    Activations Density 0.734%

    No Known Activations