© 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. 60462
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports performance and outcomes

    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
     nackte
    -0.09
    adesh
    -0.07
    LLU
    -0.07
    atsu
    -0.07
    Äł
    -0.07
    /npm
    -0.07
    irling
    -0.07
    )))),
    -0.07
    irez
    -0.07
    ModelIndex
    -0.07
    POSITIVE LOGITS
    oke
    0.07
     Tort
    0.06
    tor
    0.06
    æĵ
    0.06
     Integral
    0.06
    yp
    0.06
    rescia
    0.06
    ãĥ¼ãĤ¯
    0.06
     thanks
    0.05
     Tweet
    0.05
    Activations Density 0.034%

    No Known Activations