© 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. 77302
    Prev
    Next
    INDEX
    Explanations

    references to physical characteristics and experiences with headphones

    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
    лаÑĤи
    -0.08
    Ùĥرة
    -0.08
    .setFill
    -0.08
    arem
    -0.07
     ì¡
    -0.07
    erif
    -0.07
    ÏĦεÏħ
    -0.07
    lamaz
    -0.07
    жд
    -0.07
    /Peak
    -0.07
    POSITIVE LOGITS
     activities
    0.09
     active
    0.07
    activities
    0.07
    ernet
    0.07
     activity
    0.07
     during
    0.07
     Activities
    0.06
    Activities
    0.06
     pool
    0.06
    æĪ¶
    0.06
    Activations Density 0.028%

    No Known Activations