© 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. 31432
    Prev
    Next
    INDEX
    Explanations

    trace and traceback

    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
    ness
    -0.12
    utherland
    -0.10
    traffic
    -0.10
    teil
    -0.10
    ss
    -0.10
    semble
    -0.10
    виг
    -0.09
    rowser
    -0.09
    sWith
    -0.09
    rio
    -0.09
    POSITIVE LOGITS
    ability
    0.19
    backs
    0.18
    .Trace
    0.16
    able
    0.16
    back
    0.16
    oute
    0.15
     Trace
    0.15
    (trace
    0.14
    .trace
    0.14
     trace
    0.13
    Activations Density 0.013%

    No Known Activations