© 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. 85396
    Prev
    Next
    INDEX
    Explanations

    references to sports events and their scheduling

    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
    eways
    -0.08
    ụ
    -0.08
    iteit
    -0.07
    ạ
    -0.07
    agara
    -0.07
    iske
    -0.07
    opsis
    -0.06
    eway
    -0.06
    asca
    -0.06
     Kurd
    -0.06
    POSITIVE LOGITS
    -long
    0.08
    ãĢħ
    0.07
    long
    0.07
    ley
    0.06
    lets
    0.06
    амп
    0.06
    strom
    0.06
    ason
    0.06
    strain
    0.06
    åĪĬ
    0.06
    Activations Density 0.008%

    No Known Activations