© 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. 16104
    Prev
    Next
    INDEX
    Explanations

    pybrain.structure and supervised trainers

    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
    fty
    -0.14
    .printStackTrace
    -0.14
    <|begin_of_text|>
    -0.12
    olumn
    -0.12
    atrix
    -0.09
     McGill
    -0.09
    endregion
    -0.09
    å¾ĵ
    -0.09
     Tyto
    -0.09
     Baz
    -0.08
    POSITIVE LOGITS
    RLF
    0.09
     CascadeType
    0.09
     erotik
    0.09
    orre
    0.08
    ev
    0.08
    fcn
    0.08
    _GU
    0.08
    ForResource
    0.08
     paran
    0.08
    StartPosition
    0.08
    Activations Density 0.014%

    No Known Activations