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. 65469
    Prev
    Next
    INDEX
    Explanations

    JSON and code snippets

    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
     McMahon
    -0.09
    åĺĽ
    -0.08
     Leak
    -0.08
     Sap
    -0.08
    adil
    -0.07
    cron
    -0.07
    /in
    -0.07
     swe
    -0.07
     огÑĢа
    -0.07
    meli
    -0.07
    POSITIVE LOGITS
    ".$_
    0.09
    Actualizar
    0.08
    OffsetTable
    0.08
    .scalablytyped
    0.08
    @brief
    0.07
    æĬ
    0.07
    onom
    0.07
     SPL
    0.07
    again
    0.07
    hawks
    0.07
    Activations Density 0.009%

    No Known Activations