© 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. 32686
    Prev
    Next
    INDEX
    Explanations

    `<|start_header_id|>`, `<|end_header_id|>` structure

    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
    apon
    -0.10
     Strand
    -0.09
    uš
    -0.09
     Canter
    -0.08
    abwe
    -0.08
    âī§
    -0.08
     Editorial
    -0.08
    FINITY
    -0.08
     Agr
    -0.08
     Dixon
    -0.08
    POSITIVE LOGITS
     lob
    0.10
    mente
    0.10
    most
    0.09
    izzy
    0.09
    ÏĩÏĮ
    0.09
    gest
    0.08
    /full
    0.08
    htags
    0.08
    phem
    0.08
    (er
    0.08
    Activations Density 0.286%

    No Known Activations