© 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. 61689
    Prev
    Next
    INDEX
    Explanations

    transcript of

    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
     Emerson
    -0.12
    kea
    -0.09
    PathComponent
    -0.09
     ​​
    -0.09
    entina
    -0.09
    abaj
    -0.08
    izr
    -0.08
     migrationBuilder
    -0.08
    award
    -0.08
    óln
    -0.08
    POSITIVE LOGITS
    ed
    0.15
    /trans
    0.15
    ive
    0.13
    ural
    0.12
    omic
    0.12
     speech
    0.12
    ued
    0.12
    al
    0.12
    ively
    0.11
    ations
    0.11
    Activations Density 0.032%

    No Known Activations