© 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. 119690
    Prev
    Next
    INDEX
    Explanations

    references to specific dates, particularly those related to significant events

    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
    arkin
    -0.07
    erva
    -0.07
    531
    -0.07
    akin
    -0.07
     Tk
    -0.06
     Giang
    -0.06
    ruc
    -0.06
    oui
    -0.06
    acer
    -0.06
    pace
    -0.06
    POSITIVE LOGITS
    รà¸ģ
    0.07
    /fw
    0.07
    .sul
    0.07
    è´¸
    0.07
    omi
    0.07
    _OW
    0.06
    лÑĸÑĤ
    0.06
    Ñıн
    0.06
    ãģıãģł
    0.06
    dain
    0.06
    Activations Density 0.003%

    No Known Activations