© 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. 17-LLAMASCOPE-RES-131K
    11. 58036
    Prev
    Next
    INDEX
    Explanations

    references to religious membership and community 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
    arine
    -0.07
    essen
    -0.07
    ASET
    -0.07
    assen
    -0.07
    eton
    -0.07
    uno
    -0.07
    ail
    -0.07
    averse
    -0.07
    outu
    -0.07
    álo
    -0.07
    POSITIVE LOGITS
    ëĮĢë¡ľ
    0.06
    GPC
    0.06
     ske
    0.06
     adult
    0.06
     part
    0.06
     stage
    0.06
     texts
    0.06
     step
    0.06
     adults
    0.06
    alto
    0.06
    Activations Density 0.001%

    No Known Activations