© 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. 21553
    Prev
    Next
    INDEX
    Explanations

    prevent, stop, caught

    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
    arella
    -0.10
     restraining
    -0.09
     erad
    -0.09
     distractions
    -0.09
     suppression
    -0.09
     Hick
    -0.09
     restrain
    -0.09
     distraction
    -0.09
     eventual
    -0.09
     repression
    -0.09
    POSITIVE LOGITS
     prevent
    0.50
     preventing
    0.44
     prevented
    0.42
     prevents
    0.42
     Prevent
    0.37
    prevent
    0.35
     prevention
    0.33
    .preventDefault
    0.32
    .prevent
    0.32
    éĺ²
    0.32
    Activations Density 0.107%

    No Known Activations