© 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. 128915
    Prev
    Next
    INDEX
    Explanations

    actions related to navigating a computer system interface

    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
    elight
    -0.07
    ves
    -0.07
    cad
    -0.06
    rad
    -0.06
    ands
    -0.06
    visor
    -0.06
    .DAL
    -0.06
     div
    -0.06
    iy
    -0.06
    rh
    -0.06
    POSITIVE LOGITS
    åĪļ
    0.07
    ä¹ħä¹ħ
    0.07
    _##
    0.07
    \htdocs
    0.07
    _bulk
    0.07
    ØŃر
    0.06
    /cop
    0.06
    endale
    0.06
    ±
    0.06
     Bened
    0.06
    Activations Density 0.006%

    No Known Activations