© 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. 92921
    Prev
    Next
    INDEX
    Explanations

    references to analytics and data analysis in social media contexts

    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
    stoff
    -0.08
     Independ
    -0.07
    TypeInfo
    -0.06
    esel
    -0.06
     Messaging
    -0.06
    ersen
    -0.06
    ikip
    -0.06
    agma
    -0.06
    enou
    -0.06
    aÅĻ
    -0.06
    POSITIVE LOGITS
     tool
    0.08
     tools
    0.08
     Tool
    0.08
     reports
    0.08
    tool
    0.07
     Tools
    0.07
    -dashboard
    0.07
    reports
    0.07
    Tool
    0.07
    report
    0.07
    Activations Density 0.003%

    No Known Activations