© 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. 69242
    Prev
    Next
    INDEX
    Explanations

    references to caffeine consumption and its effects on sleep

    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
     å§
    -0.06
     brunch
    -0.06
    ragen
    -0.06
    larg
    -0.06
    .obs
    -0.06
    .opens
    -0.06
    нина
    -0.06
    97
    -0.06
    amera
    -0.06
    .snap
    -0.06
    POSITIVE LOGITS
    illow
    0.07
     bedroom
    0.07
    illard
    0.06
    TIMER
    0.06
    -bed
    0.06
    INDOW
    0.06
    uben
    0.06
    lesi
    0.06
    ndo
    0.06
    obao
    0.06
    Activations Density 0.008%

    No Known Activations