© 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. 94672
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or entities related to a place

    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
    izer
    -0.07
    mare
    -0.06
    clipse
    -0.06
    ary
    -0.06
    _putstr
    -0.06
    andro
    -0.06
    arDown
    -0.06
    ضة
    -0.06
    abis
    -0.06
    ÙĬراÙĨ
    -0.06
    POSITIVE LOGITS
    rance
    0.07
    illas
    0.07
    olla
    0.07
    mented
    0.07
    lotte
    0.07
    ulace
    0.06
    issen
    0.06
    QUE
    0.06
    izo
    0.06
    pedo
    0.06
    Activations Density 0.014%

    No Known Activations