© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 599
    Prev
    Next
    INDEX
    Explanations

    reporting actions or statements

    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
    RequestMethod
    -0.10
    iner
    -0.10
    abwe
    -0.09
    qd
    -0.08
     emblem
    -0.08
    меÑĢик
    -0.08
    ASTER
    -0.08
    raft
    -0.08
    amate
    -0.08
     faults
    -0.08
    POSITIVE LOGITS
     SAY
    0.12
     say
    0.12
    will
    0.11
     aku
    0.10
     saya
    0.10
     ÑģказаÑĤÑĮ
    0.10
    say
    0.10
     sẽ
    0.10
     Admission
    0.10
     will
    0.10
    Activations Density 0.009%

    No Known Activations