© 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. 15-LLAMASCOPE-RES-131K
    11. 88258
    Prev
    Next
    INDEX
    Explanations

    terms related to sports equipment and proper usage

    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
    oda
    -0.07
    isk
    -0.06
    åĨ
    -0.06
     Spir
    -0.06
    ante
    -0.06
    ITT
    -0.06
    tol
    -0.06
    acco
    -0.06
    pod
    -0.06
     vill
    -0.06
    POSITIVE LOGITS
    aeda
    0.07
    -handle
    0.07
     ply
    0.07
    μβ
    0.07
    /Dk
    0.06
    rossover
    0.06
    ¬¬
    0.06
    æı¡
    0.06
     Decay
    0.06
    PING
    0.06
    Activations Density 0.000%

    No Known Activations