© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 105536
    Prev
    Next
    INDEX
    Explanations

    geographical references related to the tropical Pacific and Atlantic regions, particularly in relation to environmental changes and uncertainties

    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
    viron
    -0.07
     Communities
    -0.07
    jer
    -0.07
    bourg
    -0.07
     FOREIGN
    -0.07
     Foreign
    -0.07
     пÑĢоÑģ
    -0.06
    unities
    -0.06
    .ud
    -0.06
    opus
    -0.06
    POSITIVE LOGITS
     globally
    0.09
     global
    0.08
     globals
    0.07
    glob
    0.07
     Global
    0.07
    Global
    0.06
     regions
    0.06
     Cruc
    0.06
    .Global
    0.06
    _global
    0.06
    Activations Density 0.051%

    No Known Activations