© 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. 38237
    Prev
    Next
    INDEX
    Explanations

    the followed by sentence starters

    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
    Negative Logits
    675
    -0.10
    otr
    -0.09
    908
    -0.08
    ::::::::::::
    -0.08
    .ServiceModel
    -0.08
    _requested
    -0.08
    errupted
    -0.08
     Cous
    -0.08
     Lange
    -0.08
    ches
    -0.08
    POSITIVE LOGITS
     song
    0.21
     poem
    0.17
     sentence
    0.13
     dish
    0.13
    song
    0.12
     message
    0.12
     recipe
    0.12
     piece
    0.12
     joke
    0.11
     story
    0.11
    Activations Density 0.151%

    No Known Activations