© 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. 74338
    Prev
    Next
    INDEX
    Explanations

    numerical statistics and data related to performance records in sports

    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
    800
    -0.07
    andro
    -0.06
    andin
    -0.06
     á»
    -0.06
    rene
    -0.06
    .getMinutes
    -0.06
    ord
    -0.06
     Yüz
    -0.05
     ÑĢÑĥ
    -0.05
    860
    -0.05
    POSITIVE LOGITS
     twice
    0.10
     multiple
    0.08
     counting
    0.08
     Twice
    0.08
     getCount
    0.07
    multiple
    0.07
    ultiple
    0.07
     frequent
    0.07
    requent
    0.07
     Multiple
    0.07
    Activations Density 0.008%

    No Known Activations