© 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. 40335
    Prev
    Next
    INDEX
    Explanations

    promote ethical and legal behavior

    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
     ãĢī
    -0.10
     effic
    -0.09
     discipl
    -0.09
     Pom
    -0.09
    uluk
    -0.09
    isy
    -0.09
     Hud
    -0.09
    .gr
    -0.09
     discipline
    -0.09
     trial
    -0.08
    POSITIVE LOGITS
     positive
    0.15
    positive
    0.14
     safe
    0.13
     safer
    0.13
     safety
    0.13
    Positive
    0.12
     Harm
    0.12
    safe
    0.12
    -positive
    0.12
     ê¸
    0.12
    Activations Density 0.099%

    No Known Activations