© 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. 53733
    Prev
    Next
    INDEX
    Explanations

    phrases related to offerings or availability of products and services

    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
    engo
    -0.08
    ne
    -0.07
    egen
    -0.07
    imoto
    -0.06
    ethe
    -0.06
     wing
    -0.06
    hn
    -0.06
     Rao
    -0.06
    ivot
    -0.06
    isel
    -0.06
    POSITIVE LOGITS
    PÅĻi
    0.08
    PÅĻed
    0.07
     Crossing
    0.07
    Když
    0.07
    ynomial
    0.07
    allet
    0.07
    treeview
    0.07
     moc
    0.07
    ebi
    0.07
    ylko
    0.07
    Activations Density 0.002%

    No Known Activations