© 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 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. 83138
    Prev
    Next
    INDEX
    Explanations

    phrases related to durations and time associated with processes

    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
    embre
    -0.06
     spr
    -0.06
     cof
    -0.05
     apl
    -0.05
     Rif
    -0.05
     Spr
    -0.05
    957
    -0.05
    958
    -0.05
     Colbert
    -0.05
    956
    -0.05
    POSITIVE LOGITS
    ëĭ¹
    0.08
    rokes
    0.07
    /Foundation
    0.07
    icken
    0.07
    Äįek
    0.07
    sted
    0.07
    anten
    0.06
    ÑĢак
    0.06
    son
    0.06
    sel
    0.06
    Activations Density 0.018%

    No Known Activations