© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 29854
    Prev
    Next
    INDEX
    Explanations

    when followed by pronouns or verbs

    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
    omik
    -0.10
    emek
    -0.10
    rire
    -0.10
     Gree
    -0.09
    @nate
    -0.09
    ëĶĶìĭľ
    -0.09
    Ú¯ÛĮر
    -0.09
    aeda
    -0.09
    .gdx
    -0.09
    .IsNullOr
    -0.09
    POSITIVE LOGITS
    soever
    0.17
    ver
    0.14
     it
    0.12
    -ever
    0.12
     compared
    0.12
    EVER
    0.11
     they
    0.10
    alc
    0.10
     clearly
    0.10
    -либо
    0.10
    Activations Density 0.093%

    No Known Activations