© 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. 119301
    Prev
    Next
    INDEX
    Explanations

    elements and structure associated with mathematical or formal definitions and examples

    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
    adian
    -0.07
    oler
    -0.07
    gium
    -0.07
    strcasecmp
    -0.07
     плоÑīад
    -0.07
    braco
    -0.07
    arshal
    -0.06
    彦
    -0.06
    екÑĤи
    -0.06
    idian
    -0.06
    POSITIVE LOGITS
    âĢĮ
    0.06
    acha
    0.06
     Rut
    0.06
    404
    0.06
    ypad
    0.06
     âģ
    0.06
    571
    0.06
    üstü
    0.06
     Brock
    0.06
     Leslie
    0.05
    Activations Density 0.017%

    No Known Activations