© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 75686
    Prev
    Next
    INDEX
    Explanations

    references related to college football teams and players, particularly focusing on Iowa State and Notre Dame

    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
    adera
    -0.08
    ocular
    -0.06
    culo
    -0.06
     Kou
    -0.06
    fel
    -0.06
    Defaults
    -0.06
    tur
    -0.06
     nằm
    -0.06
    nee
    -0.06
     EXP
    -0.06
    POSITIVE LOGITS
    Mob
    0.07
    Ãło
    0.07
     logo
    0.07
     unidentified
    0.07
    eria
    0.06
    aset
    0.06
    .Magenta
    0.06
    efe
    0.06
    auc
    0.06
    eka
    0.06
    Activations Density 0.008%

    No Known Activations