© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 13750
    Prev
    Next
    INDEX
    Explanations

    new able

    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
    é§ħå¾ĴæŃ©
    -0.12
    ï¼ŁãĢį\n\n
    -0.10
    çĦ¡ãģĹãģ
    -0.10
    aab
    -0.10
    ãĥĭãĥĭ
    -0.09
    çĽijåIJ¬é¡µéĿ¢
    -0.09
     çĻº
    -0.09
    arak
    -0.09
    çļĦäºĭæĥħ
    -0.09
    ï¼ģãĢį\n\n
    -0.09
    POSITIVE LOGITS
     tong
    0.10
     Dul
    0.09
     dec
    0.09
    aver
    0.08
     luck
    0.08
     ins
    0.08
     equal
    0.08
     Ped
    0.08
    å®Ļ
    0.08
     ún
    0.08
    Activations Density 0.143%

    No Known Activations