© 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. 3637
    Prev
    Next
    INDEX
    Explanations

    references to competitive sporting achievements and player accolades

    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
    ãĥ¼ãĥį
    -0.07
    imler
    -0.07
    avar
    -0.07
    engan
    -0.06
    .Alpha
    -0.06
    erner
    -0.06
    UnitTest
    -0.06
    endance
    -0.06
    258
    -0.06
    ihat
    -0.06
    POSITIVE LOGITS
     winner
    0.08
     recent
    0.08
    oubted
    0.07
    winner
    0.07
     winners
    0.07
     recently
    0.07
    recent
    0.06
    Touches
    0.06
     sensation
    0.06
     sensations
    0.06
    Activations Density 0.019%

    No Known Activations