© 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. 63484
    Prev
    Next
    INDEX
    Explanations

    stop, consider, and self-evaluate

    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
    äºĨ解
    -0.10
    entine
    -0.09
    ardy
    -0.09
    atu
    -0.09
    ï¿£ï½Ģ
    -0.09
    pcf
    -0.09
    rox
    -0.08
    isman
    -0.08
     hiá»ĥu
    -0.08
    ivant
    -0.08
    POSITIVE LOGITS
     self
    0.14
     check
    0.14
     Self
    0.12
     justify
    0.11
     checks
    0.11
    check
    0.11
     Check
    0.11
     peer
    0.11
     justification
    0.10
     checking
    0.10
    Activations Density 0.201%

    No Known Activations