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. 65487
    Prev
    Next
    INDEX
    Explanations

    useful for tasks

    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
     Lexer
    -0.10
     )\n\n\n\n\n\n\n\n
    -0.09
    heimer
    -0.09
    eview
    -0.09
    annel
    -0.09
     Wilkinson
    -0.09
    ober
    -0.08
    abbr
    -0.08
    Gam
    -0.08
    .ms
    -0.08
    POSITIVE LOGITS
     task
    0.12
     halluc
    0.11
     Marian
    0.11
     Task
    0.10
     distant
    0.10
     attention
    0.09
    ä»»åĬ¡
    0.09
     domain
    0.09
     perplex
    0.09
     Glo
    0.09
    Activations Density 0.033%

    No Known Activations