© 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. 80744
    Prev
    Next
    INDEX
    Explanations

    references to academic studies and research, particularly focusing on women's, gender, and folklore studies

    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
    ovenant
    -0.09
    eee
    -0.07
    erg
    -0.07
    upil
    -0.07
    atab
    -0.07
    avors
    -0.07
    eeee
    -0.07
     Sphere
    -0.07
    åĪ¶
    -0.07
    enties
    -0.07
    POSITIVE LOGITS
    341
    0.07
    633
    0.07
    312
    0.07
    986
    0.07
     <=>
    0.06
     area
    0.06
    asin
    0.06
    j
    0.06
    way
    0.06
    316
    0.06
    Activations Density 0.010%

    No Known Activations