© 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. 34247
    Prev
    Next
    INDEX
    Explanations

    to descend a, be self-sufficient

    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
     Fest
    -0.11
    zzo
    -0.10
    -0.09
    endregion
    -0.09
    onte
    -0.09
    337
    -0.09
    <|begin_of_text|>
    -0.08
     encrypted
    -0.08
    (
    -0.08
    awks
    -0.08
    POSITIVE LOGITS
    #
    0.10
     (*((
    0.10
     jer
    0.09
    çĽijåIJ¬é¡µéĿ¢
    0.09
     caval
    0.09
    enville
    0.09
    VR
    0.08
     VR
    0.08
     Victorian
    0.08
    оÑĢоÑĪ
    0.08
    Activations Density 0.006%

    No Known Activations