© 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. 118797
    Prev
    Next
    INDEX
    Explanations

    URLs, particularly those from Wikipedia

    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
    еÑĤом
    -0.07
    .FontStyle
    -0.07
    etu
    -0.06
    oint
    -0.06
     Ont
    -0.06
    otu
    -0.06
    èĽ
    -0.06
    bu
    -0.06
     пÑĢог
    -0.06
    رÙĪØ´
    -0.06
    POSITIVE LOGITS
    /wiki
    0.11
     ÙĪÛĮÚ©ÛĮ
    0.07
    imitive
    0.07
    /en
    0.07
    Å¡ov
    0.07
    EDIA
    0.07
     enc
    0.06
    MMdd
    0.06
    лини
    0.06
    ãĤ¦ãĤ¹
    0.06
    Activations Density 0.002%

    No Known Activations