© 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. 62983
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Campbell."

    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
    fully
    -0.08
    outu
    -0.07
    ãģĦãĤĭ
    -0.07
    icism
    -0.07
    hold
    -0.07
    zelf
    -0.07
    itives
    -0.07
     logical
    -0.07
    ì§ij
    -0.07
    abella
    -0.06
    POSITIVE LOGITS
    ary
    0.08
    ians
    0.08
    ton
    0.08
    shade
    0.07
    shire
    0.07
    ites
    0.07
    sville
    0.07
    ture
    0.07
    ian
    0.07
    Å¡ak
    0.07
    Activations Density 0.005%

    No Known Activations