© 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. 88405
    Prev
    Next
    INDEX
    Explanations

    features and functionality related to technology and electronics

    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
    onacci
    -0.07
    steder
    -0.07
     Getty
    -0.06
    /share
    -0.06
    ubo
    -0.06
    ester
    -0.06
    ucken
    -0.06
    sted
    -0.06
    ocz
    -0.06
    äºĭ
    -0.06
    POSITIVE LOGITS
     usage
    0.07
    ữ
    0.07
    adesh
    0.07
     GDK
    0.07
    usage
    0.06
     charger
    0.06
     Usage
    0.06
     WINAPI
    0.06
     Activity
    0.06
     bình
    0.06
    Activations Density 0.005%

    No Known Activations