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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 25336
    Prev
    Next
    INDEX
    Explanations

    `does`, `this`, `it` activating `so`, `was`, `then`

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

    function words and punctuation that glue sentences together, especially connectors, determiners, pronouns, and auxiliary verbs.

    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
     ÃľNÄ°VERS
    -0.09
    ofire
    -0.09
     yüksel
    -0.08
     müda
    -0.08
    åı¦å¤ĸ
    -0.08
     dolaÅŁ
    -0.08
    inae
    -0.08
     ë¨
    -0.08
    ",__
    -0.08
     kaldır
    -0.08
    POSITIVE LOGITS
    edException
    0.08
     sans
    0.07
    iores
    0.07
    -svg
    0.07
    ìĹĶ
    0.07
    огод
    0.07
     controlId
    0.07
    жд
    0.07
     optarg
    0.07
    oco
    0.07
    Activations Density 0.309%

    No Known Activations