© 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. 37015
    Prev
    Next
    INDEX
    Explanations

    purpose or function phrases

    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
    anki
    -0.08
     Mell
    -0.08
     Goodman
    -0.08
    áºŃu
    -0.08
    ardy
    -0.08
    alker
    -0.08
     Uz
    -0.08
     commissions
    -0.08
    kaar
    -0.07
    udas
    -0.07
    POSITIVE LOGITS
     jä
    0.10
    ldb
    0.09
     Gib
    0.09
     engine
    0.09
     Wol
    0.09
    855
    0.09
    ufs
    0.09
    stasy
    0.09
    .hex
    0.08
    oon
    0.08
    Activations Density 0.019%

    No Known Activations