Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5487
    Prev
    Next
    INDEX
    Explanations

    references to communication methods and 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
    loh
    -0.06
    eor
    -0.06
    untas
    -0.06
    ocl
    -0.06
    ragment
    -0.06
    ocused
    -0.06
    ยà¸ĩ
    -0.05
    isman
    -0.05
    âl
    -0.05
    loven
    -0.05
    POSITIVE LOGITS
     modes
    0.15
     mode
    0.15
     formats
    0.14
     channels
    0.14
     media
    0.14
     format
    0.14
     channel
    0.14
     delivery
    0.13
     medium
    0.13
     modal
    0.13
    Activations Density 0.118%

    No Known Activations