© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 98674
    Prev
    Next
    INDEX
    Explanations

    references to academic concepts and analysis in scholarly texts

    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
    acy
    -0.07
    ey
    -0.06
    zes
    -0.06
    лÑıÑĤÑĮÑģÑı
    -0.06
     Sly
    -0.06
     Sylv
    -0.06
    اص
    -0.06
    uro
    -0.06
    921
    -0.06
    isty
    -0.06
    POSITIVE LOGITS
    еÑĢк
    0.07
    –↵↵
    0.06
    rien
    0.06
    Ú¯ÛĮ
    0.06
    :↵↵↵↵↵↵
    0.06
    interop
    0.06
    idar
    0.06
    niž
    0.06
    afx
    0.06
     èŃ
    0.06
    Activations Density 0.014%

    No Known Activations