© 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. 17-LLAMASCOPE-RES-131K
    6. 16666
    Prev
    Next
    INDEX
    Explanations

    terms related to scanning and document processing technologies

    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
    COPE
    -0.06
    iol
    -0.06
     designing
    -0.06
    ãģ¥
    -0.06
    Forbidden
    -0.06
     designers
    -0.06
     designer
    -0.06
     unlawful
    -0.06
     eclipse
    -0.05
    linger
    -0.05
    POSITIVE LOGITS
    OCR
    0.11
     OCR
    0.10
     scanner
    0.07
     scanning
    0.07
    esseract
    0.07
     Processing
    0.07
    .document
    0.07
     scan
    0.07
    Scanner
    0.07
     scans
    0.07
    Activations Density 0.006%

    No Known Activations