© 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. 17059
    Prev
    Next
    INDEX
    Explanations

    output followed by a verb

    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
    440
    -0.10
    vertisement
    -0.10
    iant
    -0.09
    ingo
    -0.09
    ysa
    -0.09
    éĵº
    -0.09
     Ñģобой
    -0.09
    ãģ¨ãģĨ
    -0.08
    hor
    -0.08
    eÅŁit
    -0.08
    POSITIVE LOGITS
    ting
    0.41
    ted
    0.31
    TING
    0.23
    ter
    0.18
    ters
    0.18
    tings
    0.17
    /input
    0.17
    /Input
    0.15
    TED
    0.14
    wards
    0.14
    Activations Density 0.031%

    No Known Activations