© 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. 89503
    Prev
    Next
    INDEX
    Explanations

    references to sports event details and broadcasting information

    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
     Incoming
    -0.06
    intree
    -0.06
    dna
    -0.06
     precisely
    -0.06
    variation
    -0.06
     Ze
    -0.06
    alias
    -0.06
    luk
    -0.06
    Incoming
    -0.06
    íĿ¬
    -0.06
    POSITIVE LOGITS
     Radio
    0.07
    iju
    0.07
    udent
    0.07
    taÅŁ
    0.07
    eci
    0.06
     radio
    0.06
    Ãło
    0.06
    ]âĢı
    0.06
     yerel
    0.06
    IOS
    0.06
    Activations Density 0.004%

    No Known Activations