© 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. 27363
    Prev
    Next
    INDEX
    Explanations

    times of need

    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
    fty
    -0.09
    ëĿ
    -0.09
    ampa
    -0.09
    ç
    -0.08
    åĭ
    -0.08
    agi
    -0.08
    legg
    -0.08
    ｡
    -0.08
    atos
    -0.08
     Puzzle
    -0.08
    POSITIVE LOGITS
     times
    0.51
    times
    0.37
     Times
    0.32
    Times
    0.31
     TIMES
    0.31
    (times
    0.28
     moments
    0.28
    -times
    0.28
    _times
    0.27
     crisis
    0.27
    Activations Density 0.107%

    No Known Activations