© 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. 22-LLAMASCOPE-RES-131K
    11. 3872
    Prev
    Next
    INDEX
    Explanations

    time-related expressions

    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
    opis
    -0.07
    zsche
    -0.07
    éļĨ
    -0.06
     æ¬
    -0.06
    acci
    -0.06
    aub
    -0.06
    sher
    -0.06
    ugins
    -0.06
     Curve
    -0.06
    DBG
    -0.06
    POSITIVE LOGITS
    rome
    0.07
    uw
    0.07
    à¥ĩशà¤ķ
    0.07
    kla
    0.07
    ussen
    0.06
    ksam
    0.06
    ymax
    0.06
    OTES
    0.06
     synd
    0.06
     Synd
    0.06
    Activations Density 0.000%

    No Known Activations