© 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. 15-LLAMASCOPE-RES-131K
    11. 86107
    Prev
    Next
    INDEX
    Explanations

    references to specific articles or provisions

    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
    vr
    -0.06
    amp
    -0.06
    cl
    -0.06
     Marie
    -0.06
    st
    -0.05
     Nas
    -0.05
    NO
    -0.05
    er
    -0.05
     marine
    -0.05
    own
    -0.05
    POSITIVE LOGITS
    umbn
    0.09
    UnderTest
    0.08
    ertino
    0.08
    utto
    0.08
    лиÑĪ
    0.08
    ưỡng
    0.08
    rador
    0.07
    eldorf
    0.07
    entai
    0.07
    imson
    0.07
    Activations Density 0.211%

    No Known Activations