© 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. 31664
    Prev
    Next
    INDEX
    Explanations

    references to time periods and market performance data

    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
    noch
    -0.07
    ifar
    -0.07
     Fey
    -0.06
    aper
    -0.06
    ogens
    -0.06
    uyen
    -0.06
    unker
    -0.06
    ching
    -0.06
    getic
    -0.06
    hen
    -0.06
    POSITIVE LOGITS
     Dün
    0.07
    ÙĬÙĦا
    0.07
    oa
    0.07
    istrovstvÃŃ
    0.07
    ruba
    0.07
    akis
    0.07
    аÑĤÑĥ
    0.06
    arResult
    0.06
    RITE
    0.06
    ugins
    0.06
    Activations Density 0.001%

    No Known Activations