© 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. 56067
    Prev
    Next
    INDEX
    Explanations

    temporal references related to time durations and historical context

    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
    tring
    -0.06
    ¡´
    -0.06
    esk
    -0.06
    lue
    -0.06
    uzzi
    -0.06
    lak
    -0.06
    _iff
    -0.06
    vertical
    -0.06
     Alta
    -0.06
    td
    -0.05
    POSITIVE LOGITS
    ago
    0.09
     Proud
    0.07
     ago
    0.07
     Agenda
    0.07
    _elapsed
    0.06
    acos
    0.06
    AGO
    0.06
     omas
    0.06
     elapsed
    0.06
     Ago
    0.06
    Activations Density 0.012%

    No Known Activations