© 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. 121555
    Prev
    Next
    INDEX
    Explanations

    discussions about emptiness and its historical significance

    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
    ucks
    -0.06
     gift
    -0.06
     dates
    -0.06
     ap
    -0.06
    epar
    -0.06
     rel
    -0.06
    udio
    -0.06
     sto
    -0.06
     Gift
    -0.05
     bases
    -0.05
    POSITIVE LOGITS
     contributors
    0.12
     Contributors
    0.10
     CONTRIBUTORS
    0.09
     essays
    0.09
     contributions
    0.09
     Papers
    0.09
     papers
    0.08
    contributors
    0.08
    papers
    0.08
    _contrib
    0.08
    Activations Density 0.022%

    No Known Activations