© 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. 18816
    Prev
    Next
    INDEX
    Explanations

    developer and publisher information for video games

    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
    .setCharacter
    -0.07
    оÑģп
    -0.07
    rary
    -0.07
    .nlm
    -0.06
    SPATH
    -0.06
    undy
    -0.06
     ç©
    -0.06
    ecret
    -0.06
     огÑĢа
    -0.06
    ÑĩаÑĶ
    -0.06
    POSITIVE LOGITS
     team
    0.08
     studio
    0.07
     studios
    0.07
    developer
    0.07
     developer
    0.07
     Studios
    0.07
     producer
    0.07
    еви
    0.07
    isko
    0.06
     Studio
    0.06
    Activations Density 0.030%

    No Known Activations