© 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. 54302
    Prev
    Next
    INDEX
    Explanations

    instances of significant events or milestones related to time and achievements

    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
    ktop
    -0.08
    (æĹ¥
    -0.07
    oce
    -0.07
    ¦¬
    -0.07
    _Native
    -0.07
    ernals
    -0.07
    ÑĢин
    -0.07
    CHASE
    -0.07
    ByExample
    -0.07
    pll
    -0.07
    POSITIVE LOGITS
     since
    0.15
    since
    0.11
     ever
    0.10
     Since
    0.10
     seit
    0.09
    Since
    0.09
     depuis
    0.09
     ÙħÙĨØ°
    0.08
     anywhere
    0.08
    _since
    0.07
    Activations Density 0.015%

    No Known Activations