© 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. 5-LLAMASCOPE-RES-131K
    11. 126793
    Prev
    Next
    INDEX
    Explanations

    code and configuration syntax for JavaScript

    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
    atty
    -0.07
    asons
    -0.07
    UpInside
    -0.06
    udge
    -0.06
     renderItem
    -0.06
    asma
    -0.06
    artz
    -0.06
    arn
    -0.06
    ARNING
    -0.06
    -D
    -0.06
    POSITIVE LOGITS
     Townsend
    0.06
    ارÛĮØ®
    0.06
    åĹ
    0.06
    Å¡ak
    0.06
     Pack
    0.06
     Pike
    0.06
     Valk
    0.06
    ÑĪев
    0.06
    (rawValue
    0.06
    AGED
    0.06
    Activations Density 0.016%

    No Known Activations