© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35266
    Prev
    Next
    INDEX
    Explanations

    a descriptive word

    np_acts-logits-general · gemini-2.5-flash-lite

    common function words that provide grammatical structure (articles, auxiliary verbs, prepositions, and complementizers) rather than content.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    æ¿
    -0.09
    ï¼Ĭ
    -0.09
    iversit
    -0.08
    -wsj
    -0.08
    ÅĻád
    -0.08
    еÑĢÑĤи
    -0.08
    toPromise
    -0.08
    #w
    -0.08
    :.:
    -0.08
     Jah
    -0.08
    POSITIVE LOGITS
     Paw
    0.08
    _normals
    0.08
    loth
    0.07
    ounce
    0.07
    _subplot
    0.07
     âĶĥ
    0.07
    podob
    0.07
    kelas
    0.07
    -posts
    0.07
    keterangan
    0.07
    Activations Density 1.542%

    No Known Activations