© 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. 71271
    Prev
    Next
    INDEX
    Explanations

    numerical data and technical specifications

    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
    /dom
    -0.07
    ÙĪÙĦÙĩ
    -0.06
    uide
    -0.06
     Kostenlos
    -0.06
    é©
    -0.06
    olt
    -0.06
    RenderTarget
    -0.06
    ì·¨
    -0.06
    reviews
    -0.06
     Reyn
    -0.06
    POSITIVE LOGITS
    avior
    0.07
    à¸ģร
    0.07
     press
    0.06
    icken
    0.06
    aviors
    0.06
     NEW
    0.06
    orge
    0.06
    NEW
    0.06
    infeld
    0.06
    ocus
    0.06
    Activations Density 0.036%

    No Known Activations