© 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. 63186
    Prev
    Next
    INDEX
    Explanations

    instances of the word "example" or "examples" followed by enumeration

    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
    ault
    -0.07
    nan
    -0.06
    ayers
    -0.06
    _FACTOR
    -0.06
    ogle
    -0.06
     Towers
    -0.06
    oku
    -0.06
    tees
    -0.06
    ester
    -0.06
    aster
    -0.06
    POSITIVE LOGITS
    HIR
    0.08
     examples
    0.07
    blick
    0.07
    (example
    0.07
    Examples
    0.07
    fone
    0.07
    ãģĪãģ°
    0.07
    examples
    0.06
     example
    0.06
     sounds
    0.06
    Activations Density 0.009%

    No Known Activations