© 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. 4905
    Prev
    Next
    INDEX
    Explanations

    is an example

    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
     Voy
    -0.10
     strm
    -0.09
    ses
    -0.09
    çĦ¡ãģĹãģ
    -0.09
     slav
    -0.09
    asher
    -0.08
     bidi
    -0.08
    ikan
    -0.08
    ivel
    -0.08
    urous
    -0.08
    POSITIVE LOGITS
     à¤ķरà¤ķ
    0.24
    íķĺìŬ
    0.24
    ãģĹãģ¦
    0.23
    larak
    0.22
    ilerek
    0.22
    íķ´ìĦľ
    0.21
    arak
    0.18
    layarak
    0.17
    ाà¤ķर
    0.17
    à¥ĩà¤ķर
    0.16
    Activations Density 0.053%

    No Known Activations