© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 121537
    Prev
    Next
    INDEX
    Explanations

    actions associated with departing or leaving a place

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    etable
    -0.07
    uai
    -0.06
    petto
    -0.06
     Research
    -0.06
    .Dto
    -0.06
    Beginning
    -0.06
    SCR
    -0.05
    tti
    -0.05
    caller
    -0.05
     Fre
    -0.05
    POSITIVE LOGITS
     exit
    0.09
    -LAST
    0.07
    exit
    0.07
    (exit
    0.07
    Exiting
    0.07
     exiting
    0.07
    .VideoCapture
    0.07
    tae
    0.07
     exits
    0.07
    CCCC
    0.06
    Activations Density 0.015%

    No Known Activations