© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 97639
    Prev
    Next
    INDEX
    Explanations

    patterns related to API request handling in code

    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
     Slam
    -0.07
    รà¸ĩ
    -0.07
    AXB
    -0.07
    eddar
    -0.07
    ardon
    -0.07
    luk
    -0.07
    arem
    -0.07
    achs
    -0.07
    esen
    -0.06
    abwe
    -0.06
    POSITIVE LOGITS
     Dank
    0.08
    Serialized
    0.06
    639
    0.06
    ÑĭÑĤ
    0.06
    ych
    0.06
     pricing
    0.06
     rib
    0.05
    Gui
    0.05
    plusplus
    0.05
    osc
    0.05
    Activations Density 0.013%

    No Known Activations