© 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. 42816
    Prev
    Next
    INDEX
    Explanations

    references to various types of media, services, and measurements

    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
    acket
    -0.07
    azar
    -0.06
    razier
    -0.06
    ifest
    -0.06
    deaux
    -0.06
    min
    -0.06
    stit
    -0.06
    áo
    -0.06
     Ch
    -0.06
    OUN
    -0.06
    POSITIVE LOGITS
    ï¿¥
    0.07
     kuru
    0.07
    aping
    0.07
    /renderer
    0.07
     incel
    0.07
     jin
    0.06
     Becker
    0.06
    -haspopup
    0.06
    nul
    0.06
    ãĤ¤ãĤº
    0.06
    Activations Density 0.027%

    No Known Activations