© 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. 9-LLAMASCOPE-RES-131K
    11. 95593
    Prev
    Next
    INDEX
    Explanations

    expressions of strong emotions or reactions

    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
    stry
    -0.07
    earch
    -0.07
    e
    -0.07
    ách
    -0.06
    er
    -0.06
    innacle
    -0.06
    ÑĢеб
    -0.06
    bard
    -0.06
    аÑĩ
    -0.06
    ra
    -0.06
    POSITIVE LOGITS
    ilter
    0.07
    ledik
    0.07
    à¹Ĩ
    0.07
     Leone
    0.06
    ÙĪسÙģ
    0.06
     trú
    0.06
    employed
    0.06
    retim
    0.06
    imde
    0.06
     sắt
    0.06
    Activations Density 0.002%

    No Known Activations