© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 81794
    Prev
    Next
    INDEX
    Explanations

    information related to caffeine and its effects on sleep

    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
     progn
    -0.07
     Crown
    -0.07
     class
    -0.06
     ret
    -0.06
     secondary
    -0.06
     vit
    -0.06
     managed
    -0.06
     death
    -0.06
     crown
    -0.06
     amph
    -0.05
    POSITIVE LOGITS
     Subjects
    0.08
    subjects
    0.08
    Subjects
    0.08
     subjects
    0.08
    -java
    0.07
    Gatt
    0.07
    gage
    0.07
     Volunteers
    0.07
    _MARKER
    0.07
    echan
    0.07
    Activations Density 0.010%

    No Known Activations