© 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. 30954
    Prev
    Next
    INDEX
    Explanations

    HTTP headers related to content type and data transfer

    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
    ocol
    -0.08
    ñana
    -0.08
    batim
    -0.08
    arella
    -0.08
    enheim
    -0.07
    à¹Ĩ
    -0.07
    abouts
    -0.07
    acent
    -0.07
    adesh
    -0.07
    abo
    -0.07
    POSITIVE LOGITS
    /use
    0.07
     Header
    0.06
     Gor
    0.06
     Tent
    0.06
    jas
    0.06
    strtolower
    0.06
    aims
    0.06
     header
    0.06
    egov
    0.06
    Viewport
    0.06
    Activations Density 0.003%

    No Known Activations