© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35925
    Prev
    Next
    INDEX
    Explanations

    CUDA _VISIBLE denied permission

    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
    .Formatter
    -0.10
     ë¸
    -0.08
    ResourceId
    -0.08
    <|begin_of_text|>
    -0.08
    ErrorHandler
    -0.07
    rtl
    -0.07
    hazi
    -0.07
    oins
    -0.07
    FixedSize
    -0.07
    åľ¨çº¿è§Ĩé¢ij
    -0.07
    POSITIVE LOGITS
    HeaderCode
    0.09
    GuidId
    0.09
    _Lean
    0.09
    racat
    0.09
    .scalablytyped
    0.08
    iParam
    0.08
    Intialized
    0.08
    bstract
    0.08
    UILayout
    0.07
    WidthSpace
    0.07
    Activations Density 0.050%

    No Known Activations