© 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. 15-LLAMASCOPE-RES-131K
    11. 61898
    Prev
    Next
    INDEX
    Explanations

    interactions involving user interface elements and events

    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
    lux
    -0.08
    баÑĩ
    -0.07
    chez
    -0.07
    .scalablytyped
    -0.07
     sond
    -0.07
    ilon
    -0.07
    ritel
    -0.07
    endir
    -0.07
     kazan
    -0.07
    stro
    -0.07
    POSITIVE LOGITS
     anywhere
    0.06
     again
    0.06
    TTY
    0.06
     Horse
    0.05
     staying
    0.05
    CLS
    0.05
     Edgar
    0.05
    524
    0.05
     marty
    0.05
     Sik
    0.05
    Activations Density 0.009%

    No Known Activations