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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 65481
    Prev
    Next
    INDEX
    Explanations

    what you see

    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
     поба
    -0.11
    dül
    -0.10
     EXEMPLARY
    -0.10
     requ
    -0.09
    ä¹Ĥ
    -0.09
    uga
    -0.08
    OperationException
    -0.08
     crab
    -0.08
    emain
    -0.08
    owitz
    -0.08
    POSITIVE LOGITS
     sees
    0.27
     seeing
    0.24
    çľĭåΰ
    0.24
     see
    0.23
     view
    0.21
     thấy
    0.21
     sehen
    0.19
     saw
    0.19
     SEE
    0.19
     vision
    0.18
    Activations Density 0.170%

    No Known Activations