© 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. 85078
    Prev
    Next
    INDEX
    Explanations

    terms related to user interactions and optimization metrics

    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
    ãĥ¼ãĤ¹ãĥĪ
    -0.07
    edu
    -0.06
    acman
    -0.06
    arged
    -0.06
    ernaut
    -0.06
    edom
    -0.06
    ãģ¡ãĤĥãĤĵ
    -0.06
    ChangedEventArgs
    -0.06
     humming
    -0.06
    IBUT
    -0.06
    POSITIVE LOGITS
    cpy
    0.07
     Kul
    0.07
    colm
    0.06
     Roths
    0.06
    (DBG
    0.06
    obus
    0.06
    rack
    0.06
     Dy
    0.06
    ÏĥÏĢ
    0.06
     sv
    0.06
    Activations Density 0.057%

    No Known Activations