© 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. 9-LLAMASCOPE-RES-131K
    11. 94849
    Prev
    Next
    INDEX
    Explanations

    terms related to football and associated concepts

    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
    embre
    -0.07
    oux
    -0.07
    ترÙĦ
    -0.07
    traction
    -0.07
    heim
    -0.07
    velle
    -0.07
    رÙĪج
    -0.06
    ovation
    -0.06
    Miss
    -0.06
    inish
    -0.06
    POSITIVE LOGITS
    ABCDE
    0.06
    XYZ
    0.05
    ih
    0.05
    eson
    0.05
     pavement
    0.05
    μον
    0.05
     hall
    0.05
     quiz
    0.05
     Bauer
    0.05
     antis
    0.05
    Activations Density 0.018%

    No Known Activations