© 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. 54566
    Prev
    Next
    INDEX
    Explanations

    questions in any language

    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
     muse
    -0.09
     Marathon
    -0.08
     Larson
    -0.08
    ña
    -0.08
     доÑģÑĤ
    -0.08
    hrad
    -0.08
    longleftrightarrow
    -0.08
     Pron
    -0.08
    pip
    -0.08
     beaut
    -0.07
    POSITIVE LOGITS
     indeed
    0.19
    ìĿ´ëĿ¼ëĬĶ
    0.14
     means
    0.14
    ëĭ¤ëĬĶ
    0.11
    ëĿ¼ëĬĶ
    0.11
    ãģ¨ãģĦãģĨ
    0.11
     Indeed
    0.10
    ĝ
    0.10
    inde
    0.10
     ìŀĪëĭ¤ëĬĶ
    0.10
    Activations Density 0.190%

    No Known Activations