© 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. 69236
    Prev
    Next
    INDEX
    Explanations

    phrases related to causality or consequences in 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
    AsyncResult
    -0.07
    idot
    -0.07
    ined
    -0.07
    edImage
    -0.06
    these
    -0.06
    ÙĤرار
    -0.06
    ActionResult
    -0.06
    beam
    -0.06
    vit
    -0.06
    vik
    -0.06
    POSITIVE LOGITS
     instead
    0.10
     aspect
    0.10
    instead
    0.09
     Aspect
    0.08
     Instead
    0.08
     aspects
    0.07
     alone
    0.07
    aspect
    0.07
     rather
    0.07
    èĢĮ
    0.06
    Activations Density 0.035%

    No Known Activations