© 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. 124555
    Prev
    Next
    INDEX
    Explanations

    statements and phrases indicating existence or state of being

    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
     Added
    -0.07
    yro
    -0.06
    кеÑĤ
    -0.06
     added
    -0.06
    inci
    -0.06
     brace
    -0.06
    _OID
    -0.06
    avor
    -0.06
    ligt
    -0.06
    Ả
    -0.06
    POSITIVE LOGITS
    zee
    0.07
    nicas
    0.07
    ogui
    0.07
    erland
    0.06
    IGGER
    0.06
    emia
    0.06
    rawer
    0.06
    Âĩ
    0.06
    erse
    0.06
    ger
    0.06
    Activations Density 0.059%

    No Known Activations