© 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. 53751
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate similarity or comparison

    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
    ysa
    -0.07
    thora
    -0.07
    odb
    -0.07
    vero
    -0.07
    edith
    -0.07
    ÄĽlÃŃ
    -0.07
    edik
    -0.07
    ırak
    -0.07
    azy
    -0.07
    bens
    -0.07
    POSITIVE LOGITS
    Sounds
    0.09
     Sounds
    0.09
     sounds
    0.09
     sounded
    0.08
     sound
    0.07
    sounds
    0.07
     Dere
    0.06
     typical
    0.06
     describing
    0.06
     a
    0.06
    Activations Density 0.008%

    No Known Activations