© 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. 108079
    Prev
    Next
    INDEX
    Explanations

    names of universities and 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
    enz
    -0.07
    avana
    -0.06
    adel
    -0.06
     ç§
    -0.06
     Myth
    -0.06
    illas
    -0.06
    олеÑĤ
    -0.06
    rech
    -0.06
    ws
    -0.05
     Universe
    -0.05
    POSITIVE LOGITS
     fitte
    0.09
    usercontent
    0.07
     UIStoryboard
    0.07
    641
    0.06
    ominator
    0.06
    ãĤ»ãĥ³ãĤ¿ãĥ¼
    0.06
    voie
    0.06
     BaseService
    0.06
    riages
    0.06
    atts
    0.06
    Activations Density 0.029%

    No Known Activations