© 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. 94858
    Prev
    Next
    INDEX
    Explanations

    references to ideologies and their implications

    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
    isko
    -0.07
    \CMS
    -0.06
     ever
    -0.06
    icho
    -0.06
    CellStyle
    -0.06
    mma
    -0.06
    ever
    -0.06
    ru
    -0.06
     nett
    -0.06
    bes
    -0.06
    POSITIVE LOGITS
    olson
    0.07
    oola
    0.07
    ÑĩоÑĹ
    0.07
     kind
    0.07
    dea
    0.06
    841
    0.06
    curring
    0.06
    isclosed
    0.06
    è´
    0.06
    ieg
    0.06
    Activations Density 0.050%

    No Known Activations