© 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. 71402
    Prev
    Next
    INDEX
    Explanations

    references to theater, arts, animals, and hobbies

    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
    akin
    -0.06
     Approach
    -0.06
    ä¸ĵ
    -0.06
    ê¸°ë¡ľ
    -0.06
     pri
    -0.06
    å°Ī
    -0.06
    ноÑģ
    -0.06
    ulk
    -0.06
     Em
    -0.06
    _ET
    -0.06
    POSITIVE LOGITS
    ViewChild
    0.07
    tember
    0.07
     anything
    0.07
    ighbor
    0.07
    iology
    0.07
    ptides
    0.07
     literature
    0.06
    ilers
    0.06
    -es
    0.06
    cfg
    0.06
    Activations Density 0.046%

    No Known Activations