© 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. 116339
    Prev
    Next
    INDEX
    Explanations

    references to sources, materials, or attributes associated with artistic or written works

    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
    ewriter
    -0.07
     fora
    -0.07
    riba
    -0.07
    .stamp
    -0.07
    GRESS
    -0.07
    åĩ¡
    -0.07
    енÑĮ
    -0.06
    semb
    -0.06
    xia
    -0.06
     stap
    -0.06
    POSITIVE LOGITS
     originals
    0.13
     original
    0.09
    original
    0.09
     оÑĢиг
    0.08
     originally
    0.08
    sources
    0.07
     Original
    0.07
    ãĥ¼ãĥĨ
    0.07
    (original
    0.07
    -original
    0.07
    Activations Density 0.018%

    No Known Activations