© 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. 121406
    Prev
    Next
    INDEX
    Explanations

    references to connections in storytelling or themes in dramatic narratives

    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
    ilder
    -0.07
     дÑĢÑĥ
    -0.06
     chap
    -0.06
     chapters
    -0.06
    æĹł
    -0.06
    -men
    -0.05
     grocery
    -0.05
    ClassLoader
    -0.05
    712
    -0.05
     prize
    -0.05
    POSITIVE LOGITS
     audience
    0.09
     audiences
    0.09
     Audience
    0.08
    Reviewed
    0.08
     performance
    0.07
     Bened
    0.07
    .performance
    0.07
    stag
    0.07
    же
    0.07
    performance
    0.07
    Activations Density 0.020%

    No Known Activations