© 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. 9-LLAMASCOPE-RES-131K
    11. 97545
    Prev
    Next
    INDEX
    Explanations

    references to themes of accountability and responsibility in relationships and societal issues

    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
    AndView
    -0.09
    ãĥŃãĥ¼
    -0.08
     eskort
    -0.08
    avl
    -0.08
    ÙĴس
    -0.07
    uraa
    -0.07
    _persona
    -0.07
    jspx
    -0.07
    Å¡em
    -0.07
     EÅŁ
    -0.07
    POSITIVE LOGITS
    frei
    0.07
    ghan
    0.06
     Marsh
    0.06
     nor
    0.06
    YO
    0.05
     Pand
    0.05
    ãĥijãĥ³
    0.05
     Anc
    0.05
    isan
    0.05
     tapered
    0.05
    Activations Density 0.038%

    No Known Activations