© 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. 15-LLAMASCOPE-RES-131K
    6. 204
    Prev
    Next
    INDEX
    Explanations

    actions and activities related to sports and recreation

    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
     Richardson
    -0.07
     Hubbard
    -0.07
    bate
    -0.07
    echn
    -0.07
    dsl
    -0.06
    ype
    -0.06
    sn
    -0.06
    agli
    -0.06
    yd
    -0.06
    à¹Ģà¸Ń
    -0.06
    POSITIVE LOGITS
     Sachs
    0.07
    /WebAPI
    0.07
     pÅĻiÄįemž
    0.07
    _exports
    0.06
     bare
    0.06
    ãĢģå°ı
    0.06
    aya
    0.06
    дÑĢеÑģ
    0.06
    allo
    0.06
    .Mapper
    0.06
    Activations Density 0.016%

    No Known Activations