© 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 EvalsExportsAPI 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. 130791
    Prev
    Next
    INDEX
    Explanations

    references to encouragement and divine motivation

    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
    éné
    -0.07
    ignon
    -0.07
    ât
    -0.07
    â
    -0.06
    ekler
    -0.06
     inertia
    -0.06
    iets
    -0.06
    .GUI
    -0.06
    Æ¡m
    -0.06
    lili
    -0.06
    POSITIVE LOGITS
    Narrated
    0.07
    cház
    0.06
    uentes
    0.06
    uj
    0.06
    -webpack
    0.06
     unto
    0.06
     escaping
    0.06
    Hints
    0.06
    ofday
    0.06
    اÙĬØ´
    0.06
    Activations Density 0.023%

    No Known Activations