© 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. 9-LLAMASCOPE-RES-131K
    11. 98998
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude towards leaders or individuals

    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
     prey
    -0.07
    ifact
    -0.06
    Ìģt
    -0.06
    asal
    -0.06
    egra
    -0.06
    omik
    -0.06
    GameOver
    -0.06
    ialis
    -0.06
    enne
    -0.06
    imson
    -0.06
    POSITIVE LOGITS
    ties
    0.06
     platform
    0.06
    uper
    0.06
     Babe
    0.05
    anks
    0.05
    hog
    0.05
    mute
    0.05
    ONSE
    0.05
     Zap
    0.05
    ervals
    0.05
    Activations Density 0.005%

    No Known Activations