© 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. 18582
    Prev
    Next
    INDEX
    Explanations

    descriptions of environmental effects and sensory experiences

    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
     thoát
    -0.07
    avras
    -0.07
    öff
    -0.07
    iffies
    -0.07
    idlo
    -0.06
    lush
    -0.06
    oload
    -0.06
     má»±c
    -0.06
    bris
    -0.06
    .dds
    -0.06
    POSITIVE LOGITS
    aku
    0.07
     Pregn
    0.06
     Signing
    0.06
    redo
    0.06
    ãĥ¬ãĥ³
    0.06
    WEB
    0.06
     signing
    0.06
     Exped
    0.06
     smart
    0.06
    é½
    0.06
    Activations Density 0.052%

    No Known Activations