© 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. 57864
    Prev
    Next
    INDEX
    Explanations

    temporal references and indicators of 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
    Äįer
    -0.07
    abwe
    -0.07
    gom
    -0.07
    unar
    -0.06
    arra
    -0.06
    indow
    -0.06
    agini
    -0.06
     менÑĮ
    -0.06
     Nav
    -0.06
    istributed
    -0.06
    POSITIVE LOGITS
     decade
    0.07
    atten
    0.06
    oto
    0.06
     throwError
    0.06
    .circular
    0.06
    arg
    0.06
     latter
    0.06
     mid
    0.06
    ienes
    0.06
     ÑĢÑĥб
    0.05
    Activations Density 0.038%

    No Known Activations