© 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. 38560
    Prev
    Next
    INDEX
    Explanations

    references to buying or owning items

    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
    oli
    -0.07
    nect
    -0.06
    athan
    -0.06
    .isActive
    -0.06
     McCart
    -0.06
    athroom
    -0.06
    reen
    -0.06
     Daly
    -0.06
    issan
    -0.06
    ioc
    -0.06
    POSITIVE LOGITS
     purchased
    0.07
    kö
    0.07
     Cooke
    0.07
    ัà¸įà¸į
    0.06
    beautiful
    0.06
     purchase
    0.06
    iasi
    0.06
    roje
    0.06
    /goto
    0.06
     acquisition
    0.06
    Activations Density 0.024%

    No Known Activations