© 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. 58206
    Prev
    Next
    INDEX
    Explanations

    search _word, Cross (x, .Please assume, took long, We offer, following settings

    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
    çĽijåIJ¬é¡µéĿ¢
    -0.19
     åıĮ线
    -0.17
    åľ¨çº¿éĺħ读
    -0.16
    éĺħ读次æķ°
    -0.15
    设计åĻ¨
    -0.15
    ãĨ
    -0.15
    çĶ³åįļ
    -0.14
     çĶ³åįļ
    -0.14
     ç¥ŀ马
    -0.13
    ãģ£ãģį
    -0.13
    POSITIVE LOGITS
    ãĢĢ
    0.23
    ãĥ»
    0.19
    ï½
    0.17
    Âģ@
    0.15
    Âģ
    0.14
    _flg
    0.13
     contents
    0.13
    .contents
    0.11
    Contents
    0.11
     Eig
    0.11
    Activations Density 0.391%

    No Known Activations