© 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. 17-LLAMASCOPE-RES-131K
    11. 84413
    Prev
    Next
    INDEX
    Explanations

    phrases indicating location or context

    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
     byt
    -0.07
    dock
    -0.07
    DSA
    -0.07
    exus
    -0.07
    ë£
    -0.07
    aven
    -0.07
    g
    -0.06
    nad
    -0.06
    udio
    -0.06
    ziel
    -0.06
    POSITIVE LOGITS
    outu
    0.07
    615
    0.06
    omba
    0.06
     Danish
    0.06
    amarin
    0.06
     COPYRIGHT
    0.05
     ê·¸ëŁ¬
    0.05
     tradition
    0.05
    /documentation
    0.05
    ape
    0.05
    Activations Density 0.018%

    No Known Activations