© 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. 106191
    Prev
    Next
    INDEX
    Explanations

    references to remote services or APIs related to database management

    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
     ма
    -0.07
    hue
    -0.06
     Accessibility
    -0.06
     нак
    -0.06
    akis
    -0.06
    à¸ļล
    -0.06
     ge
    -0.06
     Ton
    -0.06
     Brewer
    -0.06
    ÑĢой
    -0.06
    POSITIVE LOGITS
    ybrid
    0.07
     via
    0.07
     transparent
    0.07
     reform
    0.06
    íĺ¸
    0.06
     EITHER
    0.06
    ør
    0.06
    eventType
    0.06
    -transparent
    0.06
    rière
    0.06
    Activations Density 0.039%

    No Known Activations