© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 4115
    Prev
    Next
    INDEX
    Explanations

    references to performance and competition, particularly in sports contexts

    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
     queryInterface
    -0.08
    εÏĨ
    -0.07
    ibrary
    -0.07
    ngx
    -0.07
    é§Ĩ
    -0.07
    mailto
    -0.07
    /GPL
    -0.07
    ỹ
    -0.07
     Kens
    -0.07
    gnore
    -0.07
    POSITIVE LOGITS
    reasonable
    0.06
     Nationwide
    0.06
     Hybrid
    0.06
    еÑĢеÑĩ
    0.05
     nominal
    0.05
     hybrid
    0.05
     Sands
    0.05
    оÑģÑĮ
    0.05
     vibes
    0.05
     ne
    0.05
    Activations Density 0.002%

    No Known Activations