© 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. 9-LLAMASCOPE-RES-131K
    11. 95043
    Prev
    Next
    INDEX
    Explanations

    mentions of notable people and their biographical details

    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
    ennon
    -0.07
    325
    -0.07
    iscard
    -0.06
    Matchers
    -0.06
    -ish
    -0.06
    ancel
    -0.06
    ERGY
    -0.06
    hq
    -0.06
    _Release
    -0.06
    ÃŃas
    -0.06
    POSITIVE LOGITS
     semiclass
    0.07
     reluct
    0.07
    Äįel
    0.07
    ãģįãģŁ
    0.06
    yro
    0.06
    buz
    0.06
    imdi
    0.06
    Å¡et
    0.06
    ilde
    0.06
    eyen
    0.06
    Activations Density 0.001%

    No Known Activations