© 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. 107912
    Prev
    Next
    INDEX
    Explanations

    phrases related to gameplay mechanics and exploration challenges in video games

    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
    oš
    -0.06
     ni
    -0.06
     mid
    -0.06
     py
    -0.06
     mij
    -0.06
    ud
    -0.06
     thá»ķ
    -0.06
    avors
    -0.06
    лива
    -0.06
    idend
    -0.06
    POSITIVE LOGITS
    364
    0.08
    Tasks
    0.08
     tasks
    0.07
     Tasks
    0.07
    tasks
    0.07
     Incontri
    0.07
    geber
    0.07
     premise
    0.07
    hta
    0.07
    thenReturn
    0.07
    Activations Density 0.043%

    No Known Activations