© 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 EvalsExportsinterp-engineNEWAPI 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. 62037
    Prev
    Next
    INDEX
    Explanations

    time-related information, particularly in the context of events and schedules

    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
    loo
    -0.07
     Fallen
    -0.07
    lsen
    -0.07
    lingen
    -0.06
     Hüs
    -0.06
     strips
    -0.06
    ello
    -0.06
    benchmark
    -0.06
    дн
    -0.06
    _ENCODE
    -0.06
    POSITIVE LOGITS
     hour
    0.07
     až
    0.07
     Hour
    0.07
     Uhr
    0.06
    opleft
    0.06
    -hours
    0.06
    -hour
    0.06
    ilere
    0.06
    hour
    0.06
    amina
    0.06
    Activations Density 0.009%

    No Known Activations