© 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
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 37454
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs and pronouns followed by actions

    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
    ¶Į
    -0.21
    ******č\n
    -0.18
     -*-č\n
    -0.16
    .Formatter
    -0.16
    EMPLARY
    -0.16
    įng
    -0.15
    ÂĢÂĢ
    -0.15
    -------------</
    -0.15
    ¨ë¶Ģ
    -0.14
    ķãĤĵ
    -0.14
    POSITIVE LOGITS
     [_
    0.10
    (
    0.10
    ...
    0.09
    '
    0.09
    in
    0.09
    M
    0.09
    -
    0.09
    str
    0.09
    _
    0.09
    ’;
    0.08
    Activations Density 1.890%

    No Known Activations