© 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. 17-LLAMASCOPE-RES-131K
    11. 2164
    Prev
    Next
    INDEX
    Explanations

    references to contracts, amounts, and queries related to data structures

    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
    Įĵ
    -0.08
    CompleteListener
    -0.08
    oux
    -0.08
    udit
    -0.07
     заклад
    -0.07
    aeda
    -0.07
    achs
    -0.07
    ï¼¹
    -0.07
    Startup
    -0.07
    pie
    -0.06
    POSITIVE LOGITS
     now
    0.17
    now
    0.14
     agora
    0.12
     Now
    0.12
     ÑĤепеÑĢÑĮ
    0.12
     become
    0.12
     ahora
    0.12
    Now
    0.11
     NOW
    0.11
     ìĿ´ìłľ
    0.11
    Activations Density 0.039%

    No Known Activations