© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 1156
    Prev
    Next
    INDEX
    Explanations

    specific repeated references and structural elements within legal or formal documents

    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
    iola
    -0.07
    egend
    -0.07
    lesen
    -0.07
    roj
    -0.07
    ech
    -0.07
    yonel
    -0.06
    ä½Ļ
    -0.06
    anzi
    -0.06
    duino
    -0.06
    ilian
    -0.06
    POSITIVE LOGITS
     Filename
    0.06
    δή
    0.06
    NES
    0.06
    nes
    0.06
     UIBar
    0.06
     Gerard
    0.06
     Eaton
    0.05
    رÛĮز
    0.05
    nels
    0.05
     mast
    0.05
    Activations Density 0.000%

    No Known Activations