© 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. 27763
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce or describe various types of entities or organizations

    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
    undry
    -0.07
     ấy
    -0.07
    ystate
    -0.06
    izona
    -0.06
     Blizzard
    -0.06
    /gen
    -0.06
     sheet
    -0.06
     tabs
    -0.06
    erokee
    -0.06
    ãĥ¼ãĥĭ
    -0.06
    POSITIVE LOGITS
    iples
    0.07
    ayet
    0.06
     Nicholson
    0.06
    _CBC
    0.06
    linger
    0.06
     blog
    0.06
    utor
    0.06
    Łèĥ½
    0.06
     sebuah
    0.06
    atu
    0.06
    Activations Density 0.038%

    No Known Activations