© 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. 12900
    Prev
    Next
    INDEX
    Explanations

    ideas

    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
     Guth
    -0.08
     меÑĤалли
    -0.08
    uchos
    -0.08
    òng
    -0.08
    .rs
    -0.08
    uhe
    -0.08
    ÙĨاد
    -0.08
    indy
    -0.08
    Ix
    -0.08
    =*/
    -0.08
    POSITIVE LOGITS
     ideas
    0.70
     idea
    0.67
     Ideas
    0.55
    ideas
    0.52
    idea
    0.51
     Idea
    0.47
     IDEA
    0.32
    .idea
    0.32
     иде
    0.29
     fikir
    0.29
    Activations Density 0.192%

    No Known Activations