© 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. 62298
    Prev
    Next
    INDEX
    Explanations

    ten followed by various 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
     hundred
    -0.12
    ÌĨ
    -0.10
    deen
    -0.10
    oved
    -0.10
    vard
    -0.10
    oad
    -0.09
     Hundred
    -0.09
    Blockly
    -0.09
    omain
    -0.09
    IGO
    -0.09
    POSITIVE LOGITS
     Downing
    0.23
    ured
    0.17
    acious
    0.17
     Ten
    0.16
    Ten
    0.16
    ets
    0.16
     ten
    0.15
    ancy
    0.14
    acity
    0.14
    nis
    0.14
    Activations Density 0.070%

    No Known Activations