© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 129254
    Prev
    Next
    INDEX
    Explanations

    recommendations or suggestions regarding improvements or changes

    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
    анÑĮ
    -0.09
    ubb
    -0.08
    _sd
    -0.08
    _FLASH
    -0.08
    .Unity
    -0.07
    ëĮĢíķľ
    -0.07
    etros
    -0.07
    apolis
    -0.07
    наÑĤ
    -0.07
     度
    -0.07
    POSITIVE LOGITS
     soon
    0.08
     Dee
    0.06
    enger
    0.06
     Soon
    0.06
     shortly
    0.06
     final
    0.06
     well
    0.06
    aa
    0.06
     fairly
    0.06
     c
    0.06
    Activations Density 0.028%

    No Known Activations