© 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. 41971
    Prev
    Next
    INDEX
    Explanations

    culprit identification

    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
     Murder
    -0.12
     murder
    -0.11
    :async
    -0.09
     whatever
    -0.09
     intim
    -0.09
     murdered
    -0.09
    اÙĪرÛĮ
    -0.09
     homicide
    -0.09
     defenders
    -0.09
     contestant
    -0.09
    POSITIVE LOGITS
     cul
    0.26
     responsible
    0.25
     culprit
    0.22
     identity
    0.20
     suspects
    0.20
    cul
    0.20
    å¹ķ
    0.18
     behind
    0.18
     Cul
    0.18
     master
    0.17
    Activations Density 0.068%

    No Known Activations