© 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. 16951
    Prev
    Next
    INDEX
    Explanations

    numerical data related to sports statistics and records

    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
    spath
    -0.07
     бÑĥдÑĤо
    -0.06
    Ãłu
    -0.06
    ẩu
    -0.06
    itur
    -0.06
    ýt
    -0.06
    UserProfile
    -0.06
    æİĪ
    -0.05
    -Ðľ
    -0.05
    neau
    -0.05
    POSITIVE LOGITS
     zoekt
    0.07
    etch
    0.07
    imet
    0.07
    keit
    0.07
    odia
    0.06
    rlen
    0.06
     Cove
    0.06
    nels
    0.06
    906
    0.06
    831
    0.06
    Activations Density 0.023%

    No Known Activations