© 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 EvalsExportsAPI 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. 93823
    Prev
    Next
    INDEX
    Explanations

    references to racing tracks and their characteristics

    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
    //{{
    -0.07
    è¼Ŀ
    -0.06
    loor
    -0.06
    essel
    -0.06
    |i
    -0.06
    arkin
    -0.06
    anyl
    -0.06
    dda
    -0.06
    .attach
    -0.06
    ixel
    -0.06
    POSITIVE LOGITS
    eland
    0.07
     Hands
    0.07
    RIX
    0.07
     Pods
    0.07
    eldon
    0.07
    ughs
    0.07
    poÄį
    0.07
    ousse
    0.07
     Balance
    0.06
    :right
    0.06
    Activations Density 0.005%

    No Known Activations