© 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. 46054
    Prev
    Next
    INDEX
    Explanations

    not a symptom

    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
    erland
    -0.10
     unrelated
    -0.09
    ichtig
    -0.09
    opian
    -0.09
     capabilities
    -0.09
    prd
    -0.09
     Simpson
    -0.09
     Hlav
    -0.08
     lk
    -0.08
    rou
    -0.08
    POSITIVE LOGITS
     unique
    0.48
    unique
    0.41
     exclusive
    0.40
     Unique
    0.38
     specific
    0.37
    Unique
    0.36
     UNIQUE
    0.33
    exclusive
    0.32
     peculiar
    0.32
    (unique
    0.30
    Activations Density 0.224%

    No Known Activations