© 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. 63009
    Prev
    Next
    INDEX
    Explanations

    phrases related to anticipation and excitement about upcoming events or experiences

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    udo
    -0.06
     serg
    -0.06
    father
    -0.06
     nexus
    -0.06
     reaff
    -0.06
     junk
    -0.06
    öt
    -0.06
    _secs
    -0.06
     Junk
    -0.06
    éĮ
    -0.06
    POSITIVE LOGITS
    chedulers
    0.09
    ramework
    0.07
    #ac
    0.07
    cola
    0.07
    avig
    0.07
    TOOLS
    0.07
    eydi
    0.07
    atoire
    0.07
    alendar
    0.07
    ignon
    0.07
    Activations Density 1.644%

    No Known Activations