© 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. 121638
    Prev
    Next
    INDEX
    Explanations

    references to the Pope

    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
    iker
    -0.08
    naire
    -0.08
    mente
    -0.07
    oso
    -0.07
    sov
    -0.07
    istro
    -0.07
    kan
    -0.07
    ãĥ¼ãĥ©
    -0.07
    OUS
    -0.06
    andr
    -0.06
    POSITIVE LOGITS
    ye
    0.07
    IRMWARE
    0.07
     Pap
    0.07
     pap
    0.06
    jug
    0.06
     Emer
    0.06
    tober
    0.06
    870
    0.06
    less
    0.06
    lical
    0.06
    Activations Density 0.001%

    No Known Activations