© 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. 17405
    Prev
    Next
    INDEX
    Explanations

    software/language features and requirements

    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
    ä¸įæĺ¯
    -0.11
    .tc
    -0.10
    并ä¸į
    -0.10
     Heb
    -0.09
     Byl
    -0.09
    avax
    -0.09
    /generated
    -0.09
     weren
    -0.08
    doch
    -0.08
     disarm
    -0.08
    POSITIVE LOGITS
     generally
    0.17
    ãģ®æĸ¹
    0.16
     vs
    0.14
    æĽ´åĬł
    0.13
    vs
    0.12
     wins
    0.12
     tend
    0.12
     Generally
    0.11
    more
    0.11
    ä¸ĢèĪ¬
    0.11
    Activations Density 0.111%

    No Known Activations