© 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. 59412
    Prev
    Next
    INDEX
    Explanations

    code related to image processing and graphical rendering

    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
     Canter
    -0.07
    abi
    -0.07
    ecko
    -0.06
    igion
    -0.06
    _overlay
    -0.06
    wy
    -0.06
    pest
    -0.06
    dete
    -0.06
     Overlay
    -0.06
     pest
    -0.06
    POSITIVE LOGITS
     surface
    0.09
     lighting
    0.09
     Lighting
    0.08
     reflect
    0.08
     surfaces
    0.08
    surface
    0.07
    esi
    0.07
    æĿIJ
    0.07
     ray
    0.07
     scene
    0.07
    Activations Density 0.121%

    No Known Activations