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. 65518
    Prev
    Next
    INDEX
    Explanations

    JavaScript runtime

    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
    bou
    -0.09
     writ
    -0.09
     Corona
    -0.09
     Antar
    -0.08
    amm
    -0.08
     Tribunal
    -0.08
    posed
    -0.08
     orthodox
    -0.08
    ãĥĭ
    -0.08
     Ler
    -0.08
    POSITIVE LOGITS
    urette
    0.10
    à¥Ŀ
    0.09
    å±¥
    0.09
    efon
    0.08
    ;:;:
    0.08
     heav
    0.08
     prod
    0.08
     аж
    0.08
    ::::::::::::::
    0.08
    ãĥ³ãĥij
    0.08
    Activations Density 0.000%

    No Known Activations