© 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. 106037
    Prev
    Next
    INDEX
    Explanations

    elements related to artistic and technological innovation

    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
    nw
    -0.06
    legg
    -0.06
    hip
    -0.06
    å°ı说
    -0.06
     ков
    -0.06
    quest
    -0.06
    inders
    -0.06
    avl
    -0.06
    HI
    -0.06
    udy
    -0.06
    POSITIVE LOGITS
    orz
    0.07
    åºľ
    0.07
    زÙĦ
    0.07
    apesh
    0.06
    BASH
    0.06
    .fm
    0.06
     оÑĩеÑĢедÑĮ
    0.06
    enez
    0.06
     Entire
    0.06
    _macros
    0.06
    Activations Density 0.015%

    No Known Activations