© 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. 128847
    Prev
    Next
    INDEX
    Explanations

    numerical values indicating time or durations related to 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
    oller
    -0.08
    vider
    -0.07
    ubl
    -0.07
    udeau
    -0.07
    æĸ¹éĿ¢
    -0.07
    _KeyDown
    -0.07
    erate
    -0.06
    reten
    -0.06
    ahun
    -0.06
    SelectionMode
    -0.06
    POSITIVE LOGITS
     fur
    0.06
    ults
    0.06
     sob
    0.06
     equ
    0.06
    waves
    0.06
     hearts
    0.06
    bridge
    0.06
    ,lat
    0.05
     s
    0.05
    oras
    0.05
    Activations Density 0.007%

    No Known Activations