© 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. 34350
    Prev
    Next
    INDEX
    Explanations

    manage, school, study, offer, sorting, give

    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
    .scalablytyped
    -0.10
     ########.
    -0.09
    ï½ŀï½ŀ
    -0.09
    HeaderCode
    -0.09
    TextBoxColumn
    -0.09
    ï½¢
    -0.08
    ãĥ»ãĥ»ãĥ»\n\n
    -0.08
     bacheca
    -0.08
    âĦĸâĦĸ
    -0.08
    ãĥ
    -0.08
    POSITIVE LOGITS
    /
    0.08
    ching
    0.08
    ...
    0.08
    pec
    0.07
    1
    0.07
    -
    0.07
    2
    0.07
     ï½ľ
    0.07
    a
    0.07
    e
    0.07
    Activations Density 0.057%

    No Known Activations