Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 65321
    Prev
    Next
    INDEX
    Explanations

    your questions

    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
    ımızda
    -0.10
    ımızı
    -0.10
    545
    -0.09
    ımızın
    -0.08
    Triangles
    -0.08
    emain
    -0.08
    Ùĭ
    -0.08
     themselves
    -0.08
    YLES
    -0.08
     herself
    -0.08
    POSITIVE LOGITS
     your
    0.55
    ä½łçļĦ
    0.50
     ваÑĪ
    0.42
    your
    0.40
     à¤Ĩपà¤ķ
    0.38
    æĤ¨çļĦ
    0.38
     YOUR
    0.37
    Your
    0.35
     votre
    0.35
     Your
    0.34
    Activations Density 0.431%

    No Known Activations