© 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. 5984
    Prev
    Next
    INDEX
    Explanations

    definitions and explanations related to various concepts or terms

    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
    stad
    -0.06
    aked
    -0.06
    565
    -0.06
    jc
    -0.06
    udas
    -0.06
     cod
    -0.06
    des
    -0.06
    730
    -0.06
    glob
    -0.06
    ves
    -0.06
    POSITIVE LOGITS
     terms
    0.10
    terms
    0.09
     definitions
    0.09
     definition
    0.09
     Terms
    0.08
     Definitions
    0.08
    Terms
    0.07
    /terms
    0.07
    Definitions
    0.07
    definition
    0.07
    Activations Density 0.023%

    No Known Activations