© 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. 28290
    Prev
    Next
    INDEX
    Explanations

    not yet

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

    negations indicating something has not happened or does not exist.

    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
     Ever
    -0.09
    indexOf
    -0.08
    ä¸įè¿ĩ
    -0.08
    Ñĸдно
    -0.08
     ade
    -0.08
    RR
    -0.08
     mesmo
    -0.08
    гал
    -0.08
     ado
    -0.07
    kladnÃŃ
    -0.07
    POSITIVE LOGITS
     yet
    0.95
    yet
    0.75
     Yet
    0.66
    Yet
    0.64
     еÑīе
    0.52
     jeszcze
    0.51
    ãģ¾ãģł
    0.47
     еÑīÑij
    0.47
     noch
    0.46
     henüz
    0.45
    Activations Density 0.148%

    No Known Activations