© 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. 38208
    Prev
    Next
    INDEX
    Explanations

    terms related to storage solutions for overseas donations

    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
    ildo
    -0.08
    Ìģt
    -0.07
    лаз
    -0.06
    .Reporting
    -0.06
    ,↵
    -0.06
    ipsis
    -0.06
    опÑĢи
    -0.06
    ाध
    -0.06
    èĶµ
    -0.06
    erras
    -0.06
    POSITIVE LOGITS
    opper
    0.07
    bjerg
    0.07
    -ajax
    0.07
    inet
    0.07
    alat
    0.06
    andid
    0.06
    intColor
    0.06
    IFn
    0.06
    ddy
    0.06
    &o
    0.06
    Activations Density 0.002%

    No Known Activations