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. 65517
    Prev
    Next
    INDEX
    Explanations

    sevilha IA

    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
    ìľ¼ë¡ľ
    -0.17
    ex
    -0.15
    es
    -0.15
    ets
    -0.12
    ed
    -0.12
    er
    -0.12
    ا
    -0.12
    ell
    -0.12
    list
    -0.11
    ella
    -0.11
    POSITIVE LOGITS
    ts
    0.15
    lette
    0.13
    icious
    0.12
    ัà¸ģษà¸ĵ
    0.12
    ting
    0.12
    ateral
    0.12
    waukee
    0.12
    ten
    0.11
    umin
    0.11
    lection
    0.10
    Activations Density 0.076%

    No Known Activations