© 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. 21031
    Prev
    Next
    INDEX
    Explanations

    in-prefix words

    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
    gether
    -0.15
    semble
    -0.12
    ynchronously
    -0.11
    sembled
    -0.10
    oretical
    -0.10
    withstanding
    -0.10
    sembling
    -0.10
    semblies
    -0.09
    vented
    -0.09
    slaught
    -0.09
    POSITIVE LOGITS
     depth
    0.12
     situ
    0.11
    ummer
    0.10
    LineStyle
    0.10
    eras
    0.10
    ltra
    0.10
    nect
    0.10
     Depth
    0.10
    Depth
    0.10
    ners
    0.10
    Activations Density 0.076%

    No Known Activations