© 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. 9072
    Prev
    Next
    INDEX
    Explanations

    efficiency and privacy

    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
     ifndef
    -0.08
    ãĥ¼ãĥĦ
    -0.08
    lemen
    -0.08
     deren
    -0.08
    ůž
    -0.07
    FN
    -0.07
    _Lean
    -0.07
    iž
    -0.07
    fern
    -0.07
     ActionTypes
    -0.07
    POSITIVE LOGITS
     and
    0.17
     vÃł
    0.14
     của
    0.12
     и
    0.12
     ÈĻi
    0.11
    and
    0.11
    à¹ģละ
    0.10
     à¤Ķर
    0.10
     και
    0.10
     of
    0.09
    Activations Density 0.137%

    No Known Activations