© 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. 77683
    Prev
    Next
    INDEX
    Explanations

    company names and job titles related to various sectors and industries

    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
    furt
    -0.08
    kening
    -0.07
    ruc
    -0.07
    Äįel
    -0.07
    rut
    -0.07
    chu
    -0.07
    lint
    -0.07
    ersion
    -0.07
    олÑĸ
    -0.07
    beit
    -0.07
    POSITIVE LOGITS
    ahr
    0.06
     funeral
    0.06
     Premiere
    0.05
     service
    0.05
    âĢij
    0.05
    icari
    0.05
     Auto
    0.05
     Provid
    0.05
     Blades
    0.05
    utex
    0.05
    Activations Density 0.134%

    No Known Activations