© 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. 63066
    Prev
    Next
    INDEX
    Explanations

    references to playlists and their functionalities

    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
    /legal
    -0.08
    paired
    -0.07
    nyder
    -0.07
    _DECLS
    -0.07
    iked
    -0.07
    pard
    -0.07
    zw
    -0.07
    folio
    -0.07
    .MixedReality
    -0.07
    pter
    -0.07
    POSITIVE LOGITS
    ene
    0.08
    ia
    0.08
    ed
    0.07
     dÄ±ÅŁÄ±
    0.07
    tes
    0.07
    enef
    0.06
    ights
    0.06
    _arrow
    0.06
    eting
    0.06
    ng
    0.06
    Activations Density 0.002%

    No Known Activations