© 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. 9-LLAMASCOPE-RES-131K
    11. 99039
    Prev
    Next
    INDEX
    Explanations

    instances of the word "in."

    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
    ezi
    -0.07
    oron
    -0.07
    atura
    -0.07
     Trap
    -0.06
    utzer
    -0.06
    Trap
    -0.06
    rien
    -0.06
    accum
    -0.06
    usan
    -0.06
    ieber
    -0.06
    POSITIVE LOGITS
    .firebaseapp
    0.07
    ικα
    0.07
    æ¿
    0.07
    ÑĢÑĥг
    0.06
    è£ķ
    0.06
     naï
    0.06
     noble
    0.06
    kas
    0.06
     almÄ±ÅŁ
    0.06
    åĿĬ
    0.06
    Activations Density 0.000%

    No Known Activations