© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 5633
    Prev
    Next
    INDEX
    Explanations

    such as

    np_acts-logits-general · gemini-2.5-flash-lite

    message header/boundary markers and adjacent formatting tokens in chat-style transcripts.

    oai_token-act-pair · gpt-5
    Triggered by @vetterc0
    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
    Negative Logits
    celik
    -0.09
    ivec
    -0.09
    .GraphicsUnit
    -0.08
     Bilim
    -0.08
    622
    -0.08
    اسطة
    -0.08
    USTER
    -0.08
     Rakou
    -0.07
    Â
    -0.07
     navigationOptions
    -0.07
    POSITIVE LOGITS
     types
    0.13
     any
    0.10
     certain
    0.10
     different
    0.10
     specific
    0.09
     examples
    0.09
    0.09
     whether
    0.09
    ç±»åŀĭ
    0.09
     type
    0.09
    Activations Density 0.629%

    No Known Activations