© 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. 17-LLAMASCOPE-RES-131K
    11. 14493
    Prev
    Next
    INDEX
    Explanations

    terms related to object detection and prediction in various contexts, particularly in computer vision and video analysis

    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
     Tort
    -0.07
    athed
    -0.07
     Highlander
    -0.07
    acha
    -0.07
    /Framework
    -0.06
     tort
    -0.06
    uckets
    -0.06
    ä»®
    -0.06
    ingle
    -0.06
    assed
    -0.06
    POSITIVE LOGITS
    idan
    0.06
     problem
    0.06
    hol
    0.06
    /navigation
    0.06
     problems
    0.06
    .jet
    0.06
    IService
    0.06
     TMPro
    0.06
    uspend
    0.06
    vg
    0.06
    Activations Density 0.044%

    No Known Activations