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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95595
    Prev
    Next
    INDEX
    Explanations

    keywords related to ISIS and terrorism

    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
    enant
    -0.07
    lesh
    -0.07
    htable
    -0.07
    лек
    -0.07
     rowspan
    -0.07
    ultiple
    -0.07
    atcher
    -0.07
    tek
    -0.07
    eck
    -0.06
    anke
    -0.06
    POSITIVE LOGITS
    omik
    0.07
    ahat
    0.06
    obel
    0.06
    hardt
    0.06
    ROUT
    0.06
     Ta
    0.06
    instein
    0.06
    ersist
    0.06
    bart
    0.06
    (#)
    0.06
    Activations Density 0.003%

    No Known Activations