© 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. 107370
    Prev
    Next
    INDEX
    Explanations

    references to team sports and player statistics

    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
    lyph
    -0.08
     rookie
    -0.07
     rookies
    -0.07
     Sed
    -0.07
     AFL
    -0.06
     League
    -0.06
    SF
    -0.06
     sed
    -0.06
     Rookie
    -0.06
     NBA
    -0.06
    POSITIVE LOGITS
    UCKET
    0.09
     student
    0.08
     bowl
    0.08
     campus
    0.08
     chancellor
    0.08
     university
    0.08
    student
    0.08
    .student
    0.07
     Chancellor
    0.07
     students
    0.07
    Activations Density 0.607%

    No Known Activations