© 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. 131029
    Prev
    Next
    INDEX
    Explanations

    phrases related to obligations, deadlines, and payments

    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
    ²
    -0.08
    avian
    -0.07
    ne
    -0.07
    rik
    -0.07
    dea
    -0.07
    à¥Ģय
    -0.06
    news
    -0.06
    RECT
    -0.06
    rug
    -0.06
    than
    -0.06
    POSITIVE LOGITS
    eyse
    0.08
     diligence
    0.07
    ñas
    0.07
    mán
    0.07
    ighter
    0.07
    eydi
    0.07
    ceptar
    0.07
    led
    0.07
    ãĥ¥ãĥ¼
    0.07
    itted
    0.07
    Activations Density 0.020%

    No Known Activations