© 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. 370
    Prev
    Next
    INDEX
    Explanations

    statements related to intention and purpose

    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
    StackTrace
    -0.07
     tat
    -0.07
    xAC
    -0.06
     Vác
    -0.06
    atrice
    -0.06
    xit
    -0.06
    ãn
    -0.06
    661
    -0.06
    swire
    -0.06
    erne
    -0.06
    POSITIVE LOGITS
     concerned
    0.07
     concern
    0.06
    _initializer
    0.06
    agged
    0.06
    redits
    0.06
    adians
    0.06
    looking
    0.06
     seek
    0.06
    lobe
    0.06
     looking
    0.06
    Activations Density 0.053%

    No Known Activations