© 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 EvalsExportsAPI 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. 118834
    Prev
    Next
    INDEX
    Explanations

    CSS properties and HTML elements

    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
    peare
    -0.07
    åѤ
    -0.07
    uml
    -0.07
    IEWS
    -0.07
     Spot
    -0.07
    iability
    -0.06
    -spot
    -0.06
    ĥĿ
    -0.06
    cdc
    -0.06
    rung
    -0.06
    POSITIVE LOGITS
     AppBar
    0.08
    oux
    0.08
     fixed
    0.08
    -fixed
    0.07
     header
    0.07
     bar
    0.07
    .getHeader
    0.07
    bar
    0.07
    avern
    0.07
    deniz
    0.07
    Activations Density 0.020%

    No Known Activations