© 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. 21393
    Prev
    Next
    INDEX
    Explanations

    explaining basic rules

    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
     grinder
    -0.09
     Roulette
    -0.09
    okit
    -0.09
     Raven
    -0.09
     diversified
    -0.08
     rov
    -0.08
    DialogTitle
    -0.08
    TPL
    -0.08
    mouseleave
    -0.08
     Supporters
    -0.08
    POSITIVE LOGITS
     rules
    0.39
     Rules
    0.32
    rules
    0.30
    Rules
    0.26
    è§Ħ
    0.26
     rule
    0.26
     RULE
    0.24
     пÑĢавила
    0.23
    _rules
    0.23
    /rules
    0.22
    Activations Density 0.126%

    No Known Activations