© 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. 15-LLAMASCOPE-RES-131K
    11. 103350
    Prev
    Next
    INDEX
    Explanations

    references to time periods and durations

    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
    bject
    -0.07
     Eventually
    -0.07
    ectl
    -0.06
    artz
    -0.06
     eventually
    -0.06
    ẻ
    -0.06
    oid
    -0.06
    .ms
    -0.06
     cu
    -0.06
    emoc
    -0.06
    POSITIVE LOGITS
    enheim
    0.07
    IGHL
    0.07
    losures
    0.06
    ctal
    0.06
    xea
    0.06
    æĪĸ
    0.06
    439
    0.06
    962
    0.06
     or
    0.06
     contempor
    0.06
    Activations Density 0.011%

    No Known Activations