© 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. 31635
    Prev
    Next
    INDEX
    Explanations

    words related to social or civic themes and their implications

    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
    s
    -0.10
    pagen
    -0.07
    itories
    -0.07
    inta
    -0.07
    onyms
    -0.07
    anut
    -0.07
    -thumbnail
    -0.07
    outs
    -0.06
    amma
    -0.06
    peats
    -0.06
    POSITIVE LOGITS
    erto
    0.07
    hall
    0.06
    hir
    0.06
    ince
    0.06
    IBE
    0.06
    isbn
    0.06
    ugu
    0.06
    ug
    0.06
    wner
    0.06
    urn
    0.06
    Activations Density 0.230%

    No Known Activations