© 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. 17-LLAMASCOPE-RES-131K
    11. 105659
    Prev
    Next
    INDEX
    Explanations

    phrases indicating proximity or nearness in terms of location or time

    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
    mour
    -0.06
     Mastery
    -0.06
    _DEFINED
    -0.06
    ká
    -0.06
     ||=
    -0.06
    inka
    -0.06
     Fridays
    -0.06
    è¨
    -0.06
    еÑģÑĤи
    -0.06
     maj
    -0.06
    POSITIVE LOGITS
    ckett
    0.07
     Tobias
    0.07
    REA
    0.07
     ready
    0.06
    cket
    0.06
     hel
    0.06
    dbl
    0.06
    ëĭ¤ë©´
    0.06
    cci
    0.06
    avel
    0.06
    Activations Density 0.002%

    No Known Activations