© 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. 15-LLAMASCOPE-RES-131K
    11. 87091
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "evening."

    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
    sing
    -0.07
    ching
    -0.07
     richt
    -0.06
     Noon
    -0.06
    scri
    -0.06
    eras
    -0.06
    s
    -0.06
    serv
    -0.06
     mạnh
    -0.06
    jour
    -0.06
    POSITIVE LOGITS
    -night
    0.08
    lies
    0.08
    clubs
    0.08
    mares
    0.07
    ega
    0.07
    itez
    0.07
    ness
    0.07
    /e
    0.07
    quals
    0.07
     hours
    0.07
    Activations Density 0.010%

    No Known Activations