© 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. 72131
    Prev
    Next
    INDEX
    Explanations

    mentions of the football club Manchester United

    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
    ën
    -0.07
    keit
    -0.07
    puty
    -0.07
    Å¡ti
    -0.07
    ÂŃing
    -0.07
    erna
    -0.07
    ern
    -0.07
    ìį¨
    -0.07
    ITO
    -0.07
    ça
    -0.07
    POSITIVE LOGITS
    s
    0.08
    uguay
    0.07
    lify
    0.07
    931
    0.06
    _Framework
    0.06
    ató
    0.06
    esco
    0.06
    úsqueda
    0.06
     Savage
    0.06
    orado
    0.06
    Activations Density 0.008%

    No Known Activations