© 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. 72440
    Prev
    Next
    INDEX
    Explanations

    web domain extensions and email addresses

    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
    ãĤ¾
    -0.06
    praak
    -0.06
    UIColor
    -0.06
    γά
    -0.06
     sof
    -0.06
    ucci
    -0.06
    acz
    -0.06
    etrics
    -0.06
    ddy
    -0.06
     Huffman
    -0.06
    POSITIVE LOGITS
    accion
    0.06
    Å¡lo
    0.06
     Dillon
    0.06
    -gnu
    0.06
    aine
    0.06
    fak
    0.06
     Welcome
    0.06
    utterstock
    0.06
    Ä
    0.06
    akte
    0.06
    Activations Density 0.054%

    No Known Activations