© 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. 29283
    Prev
    Next
    INDEX
    Explanations

    output and results

    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
     JsonRequest
    -0.09
    .XPath
    -0.08
    actices
    -0.08
    geries
    -0.08
    veau
    -0.08
     Imports
    -0.08
    .prepareStatement
    -0.08
     MERCHANTABILITY
    -0.08
    matchCondition
    -0.08
    оÑĢод
    -0.07
    POSITIVE LOGITS
     output
    0.56
     outputs
    0.51
     results
    0.46
    output
    0.43
     Output
    0.39
    è¾ĵåĩº
    0.37
    Output
    0.35
     Outputs
    0.35
    results
    0.34
     result
    0.34
    Activations Density 0.270%

    No Known Activations