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

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 104432
    Prev
    Next
    INDEX
    Explanations

    references to specific movie franchises and their elements

    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
    鬼
    -0.08
     Amer
    -0.06
    ament
    -0.06
     Cougar
    -0.06
    554
    -0.06
     Bent
    -0.06
    ofday
    -0.06
     sel
    -0.06
     Felix
    -0.06
    ">//
    -0.06
    POSITIVE LOGITS
    unas
    0.07
     Pods
    0.07
     punct
    0.07
    allah
    0.06
    à¸²à¸Ľ
    0.06
    Bounding
    0.06
    Lens
    0.06
    ervo
    0.06
    warf
    0.06
    anzi
    0.06
    Activations Density 0.016%

    No Known Activations