© 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. 74319
    Prev
    Next
    INDEX
    Explanations

    names of universities and educational institutions

    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
    WEEN
    -0.06
    ogue
    -0.06
    hq
    -0.06
    inu
    -0.06
    anded
    -0.06
    LIC
    -0.06
     br
    -0.05
     veg
    -0.05
    entina
    -0.05
    fait
    -0.05
    POSITIVE LOGITS
    anness
    0.08
    (EC
    0.07
    yı
    0.07
    ucker
    0.07
    _nsec
    0.07
    orris
    0.07
    roken
    0.07
     Libraries
    0.07
     Law
    0.07
    utenberg
    0.07
    Activations Density 0.022%

    No Known Activations