© 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. 91620
    Prev
    Next
    INDEX
    Explanations

    emotions related to surprise or shock in various contexts

    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
    ENO
    -0.08
    ekil
    -0.08
    enumerator
    -0.08
    ableViewController
    -0.08
    lassen
    -0.07
     GENERIC
    -0.07
    ersen
    -0.07
    enderror
    -0.07
    andbox
    -0.07
    alia
    -0.07
    POSITIVE LOGITS
     many
    0.09
     everyone
    0.09
     both
    0.07
     everybody
    0.07
     wider
    0.07
     world
    0.07
    many
    0.07
     worldwide
    0.06
    ingly
    0.06
     widespread
    0.06
    Activations Density 0.017%

    No Known Activations