© 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. 30416
    Prev
    Next
    INDEX
    Explanations

    key moments of realization or understanding in a narrative context

    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
    ADDE
    -0.06
    ÐIJÑĢÑħÑĸв
    -0.06
     Posted
    -0.06
    <::
    -0.06
    luent
    -0.06
    æĺŃåĴĮ
    -0.06
     quoi
    -0.06
    QUEST
    -0.06
     Beitrag
    -0.06
     MÃľ
    -0.06
    POSITIVE LOGITS
     considering
    0.11
     consider
    0.10
     consideration
    0.10
    consider
    0.10
     considers
    0.09
     compared
    0.09
     considered
    0.09
     consid
    0.09
     Consider
    0.09
     compare
    0.09
    Activations Density 0.012%

    No Known Activations