© 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. 5500
    Prev
    Next
    INDEX
    Explanations

    Here is/are/goes

    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
    Negative Logits
    'a
    -0.10
    ella
    -0.10
     Patron
    -0.10
    458
    -0.09
    re
    -0.09
    ungs
    -0.09
    ’;a
    -0.09
    sh
    -0.08
    ss
    -0.08
    pector
    -0.08
    POSITIVE LOGITS
    after
    0.19
    ford
    0.18
    ina
    0.17
    by
    0.14
    unto
    0.13
    archical
    0.13
    INA
    0.12
    oes
    0.12
    ìłĢ
    0.11
    vana
    0.11
    Activations Density 0.084%

    No Known Activations