© 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. 130138
    Prev
    Next
    INDEX
    Explanations

    references to contact information or support details

    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
    HING
    -0.07
    âu
    -0.07
    ikan
    -0.07
     eskort
    -0.06
    INGS
    -0.06
    tero
    -0.06
    inx
    -0.06
    è¡Ŀ
    -0.06
    495
    -0.06
    ROY
    -0.06
    POSITIVE LOGITS
     Lawson
    0.07
    GraphNode
    0.07
     Guill
    0.06
     ext
    0.06
    chers
    0.06
     ãĥĨ
    0.06
    odes
    0.06
    .extensions
    0.06
     McCl
    0.06
    ocl
    0.06
    Activations Density 0.001%

    No Known Activations