© 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. 82915
    Prev
    Next
    INDEX
    Explanations

    references to the concept of taking action or engaging in activities

    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
     Iv
    -0.06
    ji
    -0.06
    acho
    -0.05
     associations
    -0.05
    جÛĮ
    -0.05
    976
    -0.05
     Par
    -0.05
     sup
    -0.05
     Gong
    -0.05
     Elder
    -0.05
    POSITIVE LOGITS
    /Dk
    0.08
    LEGRO
    0.07
    adir
    0.07
    ¬¬
    0.07
    cket
    0.07
    uyla
    0.07
    ãĤ¹ãĥĨ
    0.07
    turnstile
    0.07
    wner
    0.07
    /WebAPI
    0.07
    Activations Density 0.019%

    No Known Activations