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. 65470
    Prev
    Next
    INDEX
    Explanations

    diverse words followed by common function words

    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
    aÄŁa
    -0.08
    ãĤ¤ãĤº
    -0.08
     Warner
    -0.08
    ucz
    -0.08
    央
    -0.08
    assel
    -0.08
    ä½ľ
    -0.07
    .infinity
    -0.07
    osti
    -0.07
    _drv
    -0.07
    POSITIVE LOGITS
    com
    0.08
    rag
    0.08
     Kle
    0.08
    asso
    0.08
    aret
    0.08
    )const
    0.07
    ed
    0.07
    ee
    0.07
    ï¸ı
    0.07
    un
    0.07
    Activations Density 0.015%

    No Known Activations