© 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. 29229
    Prev
    Next
    INDEX
    Explanations

    ãģ§ãģĻãĢĤ

    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
    çĦ¡ãģĹãģ
    -0.17
    ï¼ŁãĢį\n\n
    -0.16
    ï¼ģãĢį\n\n
    -0.14
    çĽijåIJ¬é¡µéĿ¢
    -0.14
    ãĢĤãģĤ
    -0.13
    ãģĹãģªãģĦ
    -0.12
    ï¼ģï¼ģ\n\n
    -0.12
    ãĢĤãģĬ
    -0.11
    ãĢij,ãĢIJ
    -0.11
    ï¼ģ”;\n\n
    -0.11
    POSITIVE LOGITS
    s
    0.11
    .
    0.10
    ãĢĤ
    0.09
     heter
    0.09
    ghan
    0.09
     Idol
    0.09
     trib
    0.09
    oga
    0.09
    ãĢģ
    0.09
    Ư
    0.08
    Activations Density 0.029%

    No Known Activations