© 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. 91554
    Prev
    Next
    INDEX
    Explanations

    references to specific conditions or criteria in various contexts

    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
     treff
    -0.07
     very
    -0.07
    ustos
    -0.07
    ütün
    -0.06
     Downs
    -0.06
    ictor
    -0.06
    au
    -0.06
     another
    -0.06
     MUCH
    -0.06
     much
    -0.06
    POSITIVE LOGITS
    onth
    0.07
    aviest
    0.07
    æ¶ī
    0.07
    most
    0.07
     olanlar
    0.07
    weeney
    0.06
    essential
    0.06
     specifically
    0.06
     directly
    0.06
    Remaining
    0.06
    Activations Density 0.045%

    No Known Activations