© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 107133
    Prev
    Next
    INDEX
    Explanations

    references to medical practices and professional services

    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
     Schro
    -0.07
    ish
    -0.06
    ly
    -0.06
    ocz
    -0.06
    arks
    -0.06
    animated
    -0.06
     Oro
    -0.06
    roleum
    -0.06
    aces
    -0.06
    би
    -0.06
    POSITIVE LOGITS
    indy
    0.07
    ossa
    0.07
    builtin
    0.07
    üstü
    0.07
     '\''
    0.07
    automation
    0.07
    ä¼Ļ
    0.07
    preset
    0.07
    /company
    0.07
    ESP
    0.07
    Activations Density 0.006%

    No Known Activations