© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 116628
    Prev
    Next
    INDEX
    Explanations

    scenarios involving player interactions and character dynamics in a game context

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     ogs
    -0.09
    engan
    -0.08
    .intellij
    -0.08
    ellas
    -0.08
    izophren
    -0.08
    anness
    -0.08
    illas
    -0.08
    _marshall
    -0.07
    ollision
    -0.07
    chaft
    -0.07
    POSITIVE LOGITS
     McMaster
    0.06
     character
    0.06
     everyone
    0.06
    agr
    0.06
     Pur
    0.06
     everybody
    0.06
     Lester
    0.05
     turns
    0.05
     Character
    0.05
     evening
    0.05
    Activations Density 0.004%

    No Known Activations