© 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 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. 3647
    Prev
    Next
    INDEX
    Explanations

    topics related to the recognition and regulation of sports teams

    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
    allet
    -0.06
    aghan
    -0.06
     fputs
    -0.06
    463
    -0.06
    usi
    -0.06
    agner
    -0.06
     Herm
    -0.06
    maj
    -0.06
     Allen
    -0.06
    enga
    -0.05
    POSITIVE LOGITS
     legal
    0.08
     automatic
    0.07
    urope
    0.07
    Ùħز
    0.07
     official
    0.07
    legal
    0.07
     advantages
    0.06
     benefits
    0.06
    Automatic
    0.06
     protection
    0.06
    Activations Density 0.037%

    No Known Activations