© 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. 106708
    Prev
    Next
    INDEX
    Explanations

    section and column formatting indicators typically used in structured documents or papers

    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
    kish
    -0.07
    amage
    -0.07
    iona
    -0.06
    reta
    -0.06
    ota
    -0.06
     Barton
    -0.06
    оÑĤа
    -0.06
     Ä°n
    -0.06
    atars
    -0.06
    edd
    -0.06
    POSITIVE LOGITS
    OfType
    0.07
    TypeEnum
    0.07
    SubMenu
    0.07
    .LayoutStyle
    0.06
    efeller
    0.06
    iteDatabase
    0.06
     Gregg
    0.06
     Stateless
    0.06
     bon
    0.06
     بÙĪÙĦ
    0.06
    Activations Density 0.001%

    No Known Activations