© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 89879
    Prev
    Next
    INDEX
    Explanations

    phrases and vocabulary related to societal and systemic issues

    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
    okus
    -0.07
    stanov
    -0.06
    quoise
    -0.06
    anik
    -0.06
    quo
    -0.06
    umbnail
    -0.06
    neutral
    -0.06
    uces
    -0.06
     initially
    -0.06
    Raster
    -0.06
    POSITIVE LOGITS
    erver
    0.07
     Bris
    0.07
     wider
    0.07
    дам
    0.06
    θÎŃ
    0.06
    avras
    0.06
     trends
    0.06
     broader
    0.06
    erve
    0.06
     underlying
    0.06
    Activations Density 0.026%

    No Known Activations