© 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. 32876
    Prev
    Next
    INDEX
    Explanations

    acknowledging or saying

    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
    ανδ
    -0.09
    å¼ĭ
    -0.09
    aze
    -0.09
    AZE
    -0.09
     excer
    -0.08
    .jav
    -0.08
    agher
    -0.08
    eka
    -0.08
     Cain
    -0.08
    èĮĤ
    -0.08
    POSITIVE LOGITS
     saying
    0.18
     say
    0.14
     statement
    0.12
    .say
    0.11
     phrase
    0.11
     said
    0.11
     says
    0.10
     frase
    0.10
     à¤ķहन
    0.10
    说
    0.10
    Activations Density 0.191%

    No Known Activations