© 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. 17-LLAMASCOPE-RES-131K
    11. 41061
    Prev
    Next
    INDEX
    Explanations

    intense action and violence in film descriptions

    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
    aving
    -0.07
     idol
    -0.06
    oft
    -0.06
    fty
    -0.06
    apping
    -0.06
    outh
    -0.06
    enville
    -0.06
     Cunning
    -0.06
    afi
    -0.06
    ernal
    -0.06
    POSITIVE LOGITS
     sez
    0.07
    ammo
    0.07
    /Foundation
    0.07
     ÙĦدÙĬ
    0.07
    vore
    0.06
     oy
    0.06
    ÙĪÛĮÙĩ
    0.06
    ableViewController
    0.06
    iface
    0.06
     WPARAM
    0.06
    Activations Density 0.001%

    No Known Activations