© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 41339
    Prev
    Next
    INDEX
    Explanations

    references to ages and associated age-related contexts

    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
    upt
    -0.07
    jure
    -0.07
    vla
    -0.06
     radicals
    -0.06
    opak
    -0.06
     dens
    -0.06
    enco
    -0.06
    uien
    -0.06
    enthal
    -0.06
    GU
    -0.06
    POSITIVE LOGITS
    th
    0.07
     Fach
    0.06
    yo
    0.06
    -old
    0.06
    rea
    0.06
     tuá»ķi
    0.06
     barely
    0.05
    ean
    0.05
    ãĥ¼ãĥĪ
    0.05
    _brand
    0.05
    Activations Density 0.015%

    No Known Activations