© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 40903
    Prev
    Next
    INDEX
    Explanations

    code request/requirements more complete

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

    function words and basic grammatical connectors (articles, prepositions, auxiliaries, quantifiers) across languages, i.e., the sentence “glue” rather than content terms.

    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
    .Formatter
    -0.13
    ******č\n
    -0.13
    ¶Į
    -0.12
    įng
    -0.12
    EMPLARY
    -0.11
    надлеж
    -0.11
    ¦æĥħ
    -0.10
    ฺ
    -0.10
     -*-č\n
    -0.10
    ³ç´°
    -0.10
    POSITIVE LOGITS
     code
    0.21
    code
    0.17
    -code
    0.14
     Code
    0.14
    ãĤ³ãĥ¼ãĥī
    0.13
    代çłģ
    0.13
    Code
    0.13
    _code
    0.13
     ì½Ķëĵľ
    0.12
    (code
    0.11
    Activations Density 0.041%

    No Known Activations