© 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. 103887
    Prev
    Next
    INDEX
    Explanations

    references to data, performance metrics, or results

    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
    Ïħν
    -0.07
     hvÄĽ
    -0.07
    .ribbon
    -0.07
    ushman
    -0.07
    readcr
    -0.07
    erb
    -0.07
    iske
    -0.07
     tuto
    -0.06
    antes
    -0.06
    RIES
    -0.06
    POSITIVE LOGITS
    ToProps
    0.07
    еÑģа
    0.06
    ouri
    0.06
    333
    0.06
    ede
    0.06
    omo
    0.06
    roe
    0.05
    uen
    0.05
    os
    0.05
    ocker
    0.05
    Activations Density 0.022%

    No Known Activations