© 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. 63146
    Prev
    Next
    INDEX
    Explanations

    references to purchasing or acquiring certification exam materials

    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
    idon
    -0.08
    adro
    -0.07
     Laurie
    -0.07
    htag
    -0.07
    /dd
    -0.06
    midt
    -0.06
    ç¦ı
    -0.06
    ouz
    -0.06
    DATED
    -0.06
    âĢĮب
    -0.06
    POSITIVE LOGITS
    isia
    0.07
    ñas
    0.07
    rů
    0.07
     doGet
    0.07
     Hodg
    0.06
    aspers
    0.06
     SDK
    0.06
    ancel
    0.06
    978
    0.06
    anlar
    0.06
    Activations Density 0.000%

    No Known Activations