© 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. 95438
    Prev
    Next
    INDEX
    Explanations

    programming-related terminology, particularly focusing on rendering and execution in a graphic or coding context

    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
    кÑĥл
    -0.07
    ixe
    -0.07
    oo
    -0.07
    pong
    -0.07
    ÅĻÃŃz
    -0.06
    eeper
    -0.06
    ainment
    -0.06
    ools
    -0.06
    Æ¡
    -0.06
    ühl
    -0.06
    POSITIVE LOGITS
     Mori
    0.07
    ylan
    0.06
    wich
    0.06
    agn
    0.06
    ilde
    0.06
    erset
    0.06
    orp
    0.06
     Modes
    0.06
    614
    0.05
    ÂŃn
    0.05
    Activations Density 0.073%

    No Known Activations