© 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. 62723
    Prev
    Next
    INDEX
    Explanations

    genres and categories related to literature and fiction

    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
    ury
    -0.06
     bana
    -0.06
     responsible
    -0.06
     пÑĢиÑģ
    -0.06
     record
    -0.06
    cola
    -0.06
     unit
    -0.06
     Courtney
    -0.05
     Gle
    -0.05
    oo
    -0.05
    POSITIVE LOGITS
     Amazon
    0.08
    MESS
    0.07
     ê·¸ëŀĺ
    0.07
    ê·¸ëŀĺ
    0.07
     eBooks
    0.07
     Vinci
    0.07
     ï¿¥
    0.07
    -vars
    0.07
     gereken
    0.07
    ož
    0.07
    Activations Density 0.008%

    No Known Activations