© 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. 63271
    Prev
    Next
    INDEX
    Explanations

    elements of creative projects and investments

    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
     EITHER
    -0.08
    ursal
    -0.07
    imid
    -0.07
    imb
    -0.07
     either
    -0.07
     or
    -0.07
    adb
    -0.07
    ÑĤеÑĢи
    -0.07
     nor
    -0.07
    amar
    -0.07
    POSITIVE LOGITS
     because
    0.12
    because
    0.11
     porque
    0.10
     myself
    0.10
    ecause
    0.09
    Because
    0.09
     omdat
    0.09
     Because
    0.09
     yesterday
    0.09
     hoping
    0.09
    Activations Density 0.051%

    No Known Activations