© 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. 123414
    Prev
    Next
    INDEX
    Explanations

    references to specific decades

    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
    owell
    -0.09
    owitz
    -0.08
    assen
    -0.07
    elen
    -0.07
    fully
    -0.07
    è§ī
    -0.07
    san
    -0.07
    refs
    -0.07
    ilden
    -0.07
    elerik
    -0.07
    POSITIVE LOGITS
    -long
    0.10
    hands
    0.07
    long
    0.06
    aire
    0.06
    406
    0.06
    -old
    0.06
    aux
    0.06
    al
    0.06
    .Foundation
    0.06
    alist
    0.06
    Activations Density 0.007%

    No Known Activations