© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 42710
    Prev
    Next
    INDEX
    Explanations

    references to mistakes or errors in judgment

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ãģĦãĤĭ
    -0.10
    åŀ
    -0.08
    maal
    -0.08
    lox
    -0.08
     treff
    -0.08
    ãĥ¼ãĥĩ
    -0.07
    ierz
    -0.07
    rière
    -0.07
    merce
    -0.07
    riere
    -0.07
    POSITIVE LOGITS
     made
    0.10
    aken
    0.10
    -made
    0.10
    /error
    0.09
    Made
    0.08
    made
    0.08
     Made
    0.08
    /errors
    0.08
    -making
    0.08
    y
    0.07
    Activations Density 0.007%

    No Known Activations