© 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. 32368
    Prev
    Next
    INDEX
    Explanations

    a noun referring to roles

    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
     lect
    -0.12
    ollectors
    -0.11
    ellers
    -0.11
     bart
    -0.11
     incumb
    -0.11
     propriet
    -0.10
     narr
    -0.10
     Funk
    -0.10
    rollers
    -0.10
     freel
    -0.10
    POSITIVE LOGITS
     editor
    0.12
    awner
    0.11
    иÑĤелÑĮ
    0.11
    undler
    0.11
    pressor
    0.10
    itizer
    0.10
    illator
    0.10
    oader
    0.09
    igator
    0.09
    ooter
    0.09
    Activations Density 0.222%

    No Known Activations