© 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. 15328
    Prev
    Next
    INDEX
    Explanations

    descriptive elements related to architecture and design

    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
    è¼
    -0.07
    enburg
    -0.07
     fondo
    -0.07
    core
    -0.06
    822
    -0.06
    latlong
    -0.06
    _tunnel
    -0.06
    sed
    -0.06
    Init
    -0.06
    _floor
    -0.06
    POSITIVE LOGITS
     windows
    0.10
    /window
    0.09
     window
    0.08
     facade
    0.08
     faç
    0.08
     Window
    0.08
     front
    0.08
     porch
    0.08
    ipl
    0.07
    /front
    0.07
    Activations Density 0.036%

    No Known Activations