© 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. 105227
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and instructions addressing the reader

    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
    Walker
    -0.07
     Primitive
    -0.07
     Walker
    -0.06
    jerne
    -0.06
    illard
    -0.06
    hardt
    -0.06
    ampion
    -0.06
     McCoy
    -0.06
    oure
    -0.06
    ä»ķ
    -0.06
    POSITIVE LOGITS
     already
    0.09
    already
    0.07
    RIX
    0.07
     Already
    0.07
     Starting
    0.07
     starting
    0.07
    Starting
    0.07
    _ALREADY
    0.07
    pch
    0.06
     Zuk
    0.06
    Activations Density 0.014%

    No Known Activations