© 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. 105391
    Prev
    Next
    INDEX
    Explanations

    the presence of significant structural or historical elements in a narrative

    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
    ovich
    -0.08
    igans
    -0.08
    eco
    -0.07
    eldon
    -0.07
    osi
    -0.06
    ille
    -0.06
    央
    -0.06
     Mour
    -0.06
    pics
    -0.06
    ernaut
    -0.06
    POSITIVE LOGITS
    lah
    0.07
    theValue
    0.06
    ieber
    0.06
    _fact
    0.06
    èijĹ
    0.06
    ooter
    0.06
    را
    0.06
    :inline
    0.06
    ktop
    0.06
    LAY
    0.06
    Activations Density 0.032%

    No Known Activations