© 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. 126750
    Prev
    Next
    INDEX
    Explanations

    references to classic literature and film adaptations

    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
    rait
    -0.07
    .scalablytyped
    -0.07
    rellas
    -0.07
    aryawan
    -0.07
    tik
    -0.07
    imports
    -0.07
    usb
    -0.06
    fav
    -0.06
    Imports
    -0.06
    reib
    -0.06
    POSITIVE LOGITS
     Missouri
    0.09
     Mississippi
    0.08
     river
    0.07
    _bootstrap
    0.07
     Huck
    0.07
    Miss
    0.06
    .pagination
    0.06
     moll
    0.06
    ippi
    0.06
     laz
    0.06
    Activations Density 0.001%

    No Known Activations