© 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. 123515
    Prev
    Next
    INDEX
    Explanations

    file paths and directory references in code

    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
    759
    -0.07
    .prom
    -0.06
    ory
    -0.06
    ëŁī
    -0.06
    анÑĮ
    -0.06
     s
    -0.06
    erten
    -0.06
    ↵
    -0.06
    .Theme
    -0.06
     sin
    -0.06
    POSITIVE LOGITS
    /her
    0.07
    ernals
    0.07
    antal
    0.07
    others
    0.07
    /WebAPI
    0.07
    eled
    0.07
    ichern
    0.07
    sou
    0.06
    culo
    0.06
     tiá»ĥu
    0.06
    Activations Density 0.000%

    No Known Activations