© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 86398
    Prev
    Next
    INDEX
    Explanations

    references to operations or practices related to businesses and industries, particularly in agriculture and healthcare

    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
     Humph
    -0.07
    incer
    -0.07
    rottle
    -0.06
    uÃŃ
    -0.06
    .override
    -0.06
    ÏĦÎŃ
    -0.06
    ã
    -0.06
    ondon
    -0.06
    .dispatcher
    -0.06
    arendra
    -0.06
    POSITIVE LOGITS
     need
    0.09
    need
    0.08
    éľĢè¦ģ
    0.07
    Need
    0.07
     Need
    0.07
     facing
    0.07
     NEED
    0.07
     requires
    0.07
    illery
    0.07
     needs
    0.07
    Activations Density 0.025%

    No Known Activations