© 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. 18802
    Prev
    Next
    INDEX
    Explanations

    instances of dialogue and quotes in the text

    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
    etur
    -0.08
     Grill
    -0.07
     Marketable
    -0.06
    é»
    -0.06
    lan
    -0.06
    añ
    -0.06
    107
    -0.06
    orWhere
    -0.06
    æĪijçļĦ
    -0.06
     my
    -0.06
    POSITIVE LOGITS
    º
    0.07
     Stam
    0.06
    CLS
    0.06
    egot
    0.06
    assen
    0.06
    .jpeg
    0.06
    OPS
    0.06
    /loader
    0.06
    GLfloat
    0.06
     NC
    0.06
    Activations Density 0.019%

    No Known Activations