© 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. 123367
    Prev
    Next
    INDEX
    Explanations

    words that evoke intrigue or curiosity

    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
    ighton
    -0.09
    ed
    -0.08
    iday
    -0.07
    æ³ģ
    -0.07
    edin
    -0.07
    eming
    -0.07
    anje
    -0.06
    454
    -0.06
    ÑĢиг
    -0.06
    ä¹ĥ
    -0.06
    POSITIVE LOGITS
    antal
    0.07
     promise
    0.07
    ingly
    0.07
     promises
    0.07
     tease
    0.06
    Ľå»º
    0.06
    jax
    0.06
    beck
    0.06
    ebi
    0.06
    ator
    0.06
    Activations Density 0.002%

    No Known Activations