© 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. 39381
    Prev
    Next
    INDEX
    Explanations

    references to specific scenes in films or theatrical works

    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
    uu
    -0.07
    ÑĢол
    -0.06
    filesystem
    -0.06
    ÑģÑĮ
    -0.06
    edm
    -0.06
     lẽ
    -0.06
    иÑĨ
    -0.06
    yan
    -0.06
    ä¸Ī
    -0.06
    olle
    -0.06
    POSITIVE LOGITS
     scenes
    0.08
     scene
    0.07
    (scene
    0.07
    .Scene
    0.07
    (Scene
    0.07
    etter
    0.07
     Scene
    0.06
    ius
    0.06
    arge
    0.06
     Scenes
    0.06
    Activations Density 0.010%

    No Known Activations