© 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. 86367
    Prev
    Next
    INDEX
    Explanations

    formatted output or markup code elements

    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
    andi
    -0.07
    hani
    -0.06
    ONGL
    -0.06
    stad
    -0.06
    atak
    -0.06
    ahat
    -0.06
     ifndef
    -0.06
    OUGH
    -0.06
    eting
    -0.06
    cms
    -0.06
    POSITIVE LOGITS
    orde
    0.07
    ionale
    0.07
    lint
    0.06
     ëĴ
    0.06
    Ñĩина
    0.06
    ãģĭãģ®
    0.06
    uby
    0.06
    -Disposition
    0.06
    .SuspendLayout
    0.06
    ãģĵãģĿ
    0.06
    Activations Density 0.147%

    No Known Activations