© 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. 119355
    Prev
    Next
    INDEX
    Explanations

    cooking-related instructions or actions

    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
     view
    -0.07
     the
    -0.07
     a
    -0.06
     itself
    -0.06
     context
    -0.06
     status
    -0.06
     reach
    -0.06
    817
    -0.06
    ance
    -0.06
    uel
    -0.06
    POSITIVE LOGITS
     tôn
    0.09
    егоÑĢ
    0.08
    /her
    0.08
     cuales
    0.08
    HELL
    0.08
    صÙģ
    0.08
    \CMS
    0.07
    СÐŀ
    0.07
     beiden
    0.07
    лоÑĩ
    0.07
    Activations Density 0.043%

    No Known Activations