© 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. 14383
    Prev
    Next
    INDEX
    Explanations

    references to notable film careers and relationships, specifically those in Hollywood

    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
    apon
    -0.08
     currently
    -0.07
    isz
    -0.07
    ventus
    -0.07
    egr
    -0.07
    ÂĮ
    -0.06
    ailer
    -0.06
    currently
    -0.06
    allon
    -0.06
    etus
    -0.06
    POSITIVE LOGITS
    رÙĪد
    0.07
    156
    0.07
    601
    0.06
    856
    0.06
     union
    0.06
     contract
    0.06
     antim
    0.06
    194
    0.06
    195
    0.06
    ismet
    0.06
    Activations Density 0.025%

    No Known Activations