© 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. 9-LLAMASCOPE-RES-131K
    11. 96354
    Prev
    Next
    INDEX
    Explanations

    numerical values and statistical representations related to sports performance

    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
    issen
    -0.08
    emouth
    -0.07
    inqu
    -0.07
    tember
    -0.07
    imu
    -0.07
    hs
    -0.07
    LING
    -0.07
    hani
    -0.07
    edback
    -0.06
    illes
    -0.06
    POSITIVE LOGITS
     Colbert
    0.06
    ·
    0.06
    æĭ¬
    0.06
    weet
    0.06
     Sheridan
    0.06
    aise
    0.06
    ashi
    0.06
    erez
    0.06
    ulous
    0.06
    esda
    0.05
    Activations Density 0.002%

    No Known Activations