© 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 EvalsExportsAPI 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. 29757
    Prev
    Next
    INDEX
    Explanations

    mentions of features and specifications in product descriptions

    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
    èĢ
    -0.07
    åŃĿ
    -0.06
     --------------------------------------------------------------------------↵
    -0.06
    ÏĦÎŃ
    -0.06
     Fol
    -0.06
    orda
    -0.06
     Malone
    -0.06
    chter
    -0.06
     bro
    -0.06
    605
    -0.06
    POSITIVE LOGITS
     features
    0.15
    features
    0.13
     Features
    0.11
    Features
    0.10
     feature
    0.10
     FEATURES
    0.10
    /features
    0.10
     technologies
    0.09
    _features
    0.09
    -feature
    0.09
    Activations Density 0.023%

    No Known Activations