© 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 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. 87428
    Prev
    Next
    INDEX
    Explanations

    references to guided tours and historical narratives

    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
    CHAPTER
    -0.06
    ÑģÑĮ
    -0.06
    ÑĢади
    -0.06
     junk
    -0.06
    ãģĵãĤį
    -0.06
     Kern
    -0.06
    ìŀ¥
    -0.06
     wast
    -0.06
    ÃŃÅĻ
    -0.06
     undefined
    -0.06
    POSITIVE LOGITS
    Hist
    0.08
     hist
    0.08
     Hist
    0.08
     narration
    0.08
     historians
    0.08
     história
    0.07
     history
    0.07
     knowledge
    0.07
     histories
    0.07
    hist
    0.07
    Activations Density 0.023%

    No Known Activations