© 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. 28631
    Prev
    Next
    INDEX
    Explanations

    stop all

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

    the word "stop" in imperative commands or instructions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @yooniel31
    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
    OTH
    -0.11
    /cop
    -0.10
    onna
    -0.10
     starting
    -0.09
    quin
    -0.09
    ãģĬãĤĬ
    -0.09
    ingo
    -0.09
    gend
    -0.09
    anga
    -0.08
    headline
    -0.08
    POSITIVE LOGITS
    gap
    0.15
    page
    0.14
    -gap
    0.14
    per
    0.14
    PED
    0.13
    /start
    0.12
    pit
    0.12
    pped
    0.11
    light
    0.11
     cold
    0.10
    Activations Density 0.023%

    No Known Activations