© 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. 78497
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their actions in the context of events or activities

    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
    nees
    -0.06
    å¥ī
    -0.06
     Soci
    -0.06
     Arte
    -0.06
    SOC
    -0.06
     Ive
    -0.06
    CreatedBy
    -0.06
    ån
    -0.06
    iful
    -0.06
    udoku
    -0.06
    POSITIVE LOGITS
     interested
    0.08
     muá»ijn
    0.07
     interest
    0.06
     Interested
    0.06
    otal
    0.06
    qus
    0.06
    439
    0.06
    312
    0.06
    stead
    0.06
     wish
    0.06
    Activations Density 0.016%

    No Known Activations