© 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. 69029
    Prev
    Next
    INDEX
    Explanations

    expressions of contentment and collective feelings

    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
    abilia
    -0.07
    oulos
    -0.06
    zenia
    -0.06
    (éĩij
    -0.06
    kea
    -0.06
    urve
    -0.06
    öz
    -0.06
    itches
    -0.06
    GLOBALS
    -0.06
     ÙģاÙĦ
    -0.06
    POSITIVE LOGITS
    POCH
    0.07
    ainted
    0.07
    elder
    0.06
     fluids
    0.06
    enze
    0.06
     Meanwhile
    0.06
     Torch
    0.06
    ãĥ¶
    0.06
    еÑģÑĤи
    0.06
    jom
    0.06
    Activations Density 0.000%

    No Known Activations