© 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. 74706
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and references to code structures or operations

    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
    Ùıس
    -0.07
     Bilg
    -0.07
    efe
    -0.07
    ût
    -0.07
    raç
    -0.07
    icha
    -0.07
    Disallow
    -0.07
    ænd
    -0.07
    uppe
    -0.07
    endar
    -0.06
    POSITIVE LOGITS
    ↵
    0.08
    ↵↵
    0.06
     PIE
    0.06
    isol
    0.06
     tup
    0.05
     Rey
    0.05
    owa
    0.05
    ros
    0.05
    anner
    0.05
    лки
    0.05
    Activations Density 0.001%

    No Known Activations