© 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. 77171
    Prev
    Next
    INDEX
    Explanations

    references to basketball and related terminology

    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
    ymous
    -0.08
    readcr
    -0.07
    orest
    -0.07
    ouv
    -0.07
    862
    -0.07
    ãĥĢãĥ¼
    -0.07
     kry
    -0.07
    ök
    -0.07
    ERCHANT
    -0.07
    herits
    -0.07
    POSITIVE LOGITS
    oons
    0.08
    .gdx
    0.08
    oon
    0.07
    door
    0.07
    าà¸Ļ
    0.07
    rete
    0.07
    ral
    0.07
    dır
    0.06
    am
    0.06
    лам
    0.06
    Activations Density 0.014%

    No Known Activations