© 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. 76603
    Prev
    Next
    INDEX
    Explanations

    references to sports teams and their performance in competitions

    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
    å¦ĩ
    -0.08
    igure
    -0.07
    PIP
    -0.07
    婦
    -0.07
    女人
    -0.07
    okus
    -0.07
    å©
    -0.07
    arters
    -0.07
     pregnant
    -0.06
    imb
    -0.06
    POSITIVE LOGITS
     underage
    0.08
     girls
    0.08
     bunk
    0.08
     Youth
    0.07
     boys
    0.07
     youth
    0.07
     youthful
    0.07
     Mädchen
    0.07
     developmental
    0.06
    girls
    0.06
    Activations Density 0.013%

    No Known Activations