© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 46304
    Prev
    Next
    INDEX
    Explanations

    goals for, but they, return before, missed all

    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
    cÃŃ
    -0.10
    icker
    -0.09
    nave
    -0.09
    تÙĤ
    -0.09
    tah
    -0.09
    croft
    -0.09
     Laden
    -0.08
    .:.:.
    -0.08
    วà¸Ļ
    -0.08
    mazon
    -0.08
    POSITIVE LOGITS
     appearances
    0.23
     appearance
    0.21
     Appearance
    0.19
    Appearance
    0.18
    appearance
    0.16
     loan
    0.14
    Appear
    0.14
     starts
    0.14
     Starts
    0.14
     debut
    0.14
    Activations Density 0.039%

    No Known Activations