© 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. 40430
    Prev
    Next
    INDEX
    Explanations

    Si followed by em, apa, oux

    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
    ãģĬãĤĬ
    -0.11
    ophy
    -0.10
    i
    -0.10
    ales
    -0.10
    enberg
    -0.10
    zi
    -0.09
    se
    -0.09
    ostringstream
    -0.09
    urette
    -0.09
     occasions
    -0.09
    POSITIVE LOGITS
    ames
    0.17
    enna
    0.16
    oux
    0.15
    esta
    0.15
    erra
    0.13
    uated
    0.12
    uation
    0.12
    opsis
    0.12
    rot
    0.12
    empre
    0.12
    Activations Density 0.044%

    No Known Activations