© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 98586
    Prev
    Next
    INDEX
    Explanations

    references to horses and horse-related activities

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ownt
    -0.08
    lain
    -0.07
    AYOUT
    -0.07
    nown
    -0.07
    ners
    -0.07
    incinn
    -0.07
    loha
    -0.07
    _ASSUME
    -0.07
    ogue
    -0.06
    ewis
    -0.06
    POSITIVE LOGITS
    /software
    0.07
    alle
    0.07
     Certif
    0.07
    ickness
    0.07
    glyph
    0.07
    λεÏħ
    0.07
    pow
    0.06
    izontally
    0.06
    brid
    0.06
    Platforms
    0.06
    Activations Density 0.008%

    No Known Activations