© 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. 5182
    Prev
    Next
    INDEX
    Explanations

    passage or transition

    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
    CHIP
    -0.10
    OrCreate
    -0.10
    oons
    -0.10
    _exempt
    -0.09
    esub
    -0.09
    itos
    -0.09
    ayi
    -0.09
    toi
    -0.09
    ylland
    -0.09
    statt
    -0.08
    POSITIVE LOGITS
    puts
    0.26
    put
    0.22
    ogh
    0.22
    out
    0.21
    -out
    0.21
    ought
    0.18
    fare
    0.18
    ly
    0.18
    OUT
    0.18
    s
    0.17
    Activations Density 0.032%

    No Known Activations