© 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
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 2700
    Prev
    Next
    INDEX
    Explanations

    foreign pronouns and affirmations

    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
    BASH
    -0.11
    ogenerated
    -0.11
    ContentLoaded
    -0.10
    /WebAPI
    -0.10
    UNUSED
    -0.09
    antt
    -0.09
    tfoot
    -0.09
    CallCheck
    -0.09
    EmptyEntries
    -0.09
    OffsetTable
    -0.09
    POSITIVE LOGITS
     meant
    0.29
     mean
    0.20
    Mean
    0.15
     means
    0.15
     Mean
    0.15
     ment
    0.14
     said
    0.14
    mean
    0.14
     kidding
    0.13
    æĦıæĢĿ
    0.13
    Activations Density 0.150%

    No Known Activations