© 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. 55095
    Prev
    Next
    INDEX
    Explanations

    word followed by a

    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
    ãĥŃãĥ¼
    -0.08
    IIIK
    -0.08
    ILON
    -0.08
    EMA
    -0.07
    iated
    -0.07
     LoÃłi
    -0.07
    ãĤ·ãĥ¼
    -0.07
    imentary
    -0.07
    )arg
    -0.07
    /to
    -0.07
    POSITIVE LOGITS
     a
    0.20
     an
    0.15
    a
    0.15
    \ta
    0.10
    an
    0.10
    ä¸Ģç§į
    0.10
    )a
    0.10
     eine
    0.10
     een
    0.10
    _a
    0.09
    Activations Density 0.055%

    No Known Activations