© 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. 15-LLAMASCOPE-RES-131K
    11. 86313
    Prev
    Next
    INDEX
    Explanations

    discussions related to caffeine and its effects on sleep and alertness

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    yp
    -0.07
    idable
    -0.07
    typed
    -0.06
    ypy
    -0.06
     ÙģÙĪÙĤ
    -0.06
     küt
    -0.06
     pornography
    -0.06
     pym
    -0.06
     Dut
    -0.06
    tail
    -0.06
    POSITIVE LOGITS
    affer
    0.08
    åĤ
    0.08
     Tanner
    0.07
     Jacques
    0.07
     Dream
    0.07
     dreaming
    0.07
    AffineTransform
    0.07
     badge
    0.07
    aday
    0.07
     waking
    0.07
    Activations Density 0.027%

    No Known Activations