© 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. 23238
    Prev
    Next
    INDEX
    Explanations

    AI, organic, executable compound

    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
    kovi
    -0.08
    ¶Į
    -0.08
    *****\n\n
    -0.08
    SPELL
    -0.08
    cela
    -0.08
    ")==
    -0.08
    ноÑĪ
    -0.08
    reste
    -0.07
    ofilm
    -0.07
    oa
    -0.07
    POSITIVE LOGITS
     [_
    0.17
    [s
    0.14
    页éĿ¢åŃĺæ¡£å¤ĩ份
    0.12
    (sp
    0.12
    ÌĨ
    0.11
    ÌĪ
    0.10
     ​​
    0.09
    =""
    0.08
    Ìģ
    0.08
    ,,
    0.07
    Activations Density 1.465%

    No Known Activations