© 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. 17-LLAMASCOPE-RES-131K
    11. 5577
    Prev
    Next
    INDEX
    Explanations

    elements associated with action and adventure themes in storytelling

    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
    esser
    -0.07
     notas
    -0.06
    elden
    -0.06
    é¼ĵ
    -0.06
    è¹
    -0.06
    _rwlock
    -0.06
    ÙĪرت
    -0.06
    zı
    -0.06
     необ
    -0.06
    apot
    -0.06
    POSITIVE LOGITS
     scene
    0.08
     Tender
    0.07
    plet
    0.07
     tender
    0.07
    inqu
    0.06
    uish
    0.06
    roup
    0.06
     Scene
    0.06
     scenes
    0.06
     presumably
    0.06
    Activations Density 0.003%

    No Known Activations