© 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. 121601
    Prev
    Next
    INDEX
    Explanations

    references to significant events or incidents

    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
    adol
    -0.09
    sville
    -0.08
    odu
    -0.07
    aram
    -0.07
    abis
    -0.07
    ona
    -0.07
    /stdc
    -0.06
     responseBody
    -0.06
    ilda
    -0.06
    ÑĨÑĥ
    -0.06
    POSITIVE LOGITS
     iv
    0.08
    ampion
    0.06
    ocrisy
    0.06
    forder
    0.06
     SCN
    0.06
    gre
    0.06
     Unit
    0.05
     Sus
    0.05
    licted
    0.05
    esser
    0.05
    Activations Density 0.001%

    No Known Activations