© 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. 33960
    Prev
    Next
    INDEX
    Explanations

    "the" quoted dialog titles

    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
    .CustomButton
    -0.10
     button
    -0.10
    OTH
    -0.10
    oom
    -0.09
     Savage
    -0.09
    /favicon
    -0.09
    ipse
    -0.09
    button
    -0.09
    poster
    -0.09
    ifo
    -0.08
    POSITIVE LOGITS
     dialog
    0.24
     dialogue
    0.24
    dialog
    0.19
     window
    0.18
     pop
    0.17
    å¼¹
    0.15
     Dialogue
    0.15
    -dialog
    0.14
     appeared
    0.14
    _dialog
    0.14
    Activations Density 0.037%

    No Known Activations