© 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. 84941
    Prev
    Next
    INDEX
    Explanations

    references to eligibility criteria and requirements for participation 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
    fell
    -0.08
    bounce
    -0.08
    ROTO
    -0.07
    Dyn
    -0.07
    agan
    -0.07
    disposing
    -0.07
    aler
    -0.07
    avia
    -0.07
    ãĥķãĥ¬
    -0.06
    ajs
    -0.06
    POSITIVE LOGITS
     dual
    0.08
    Dual
    0.07
     choice
    0.07
     ir
    0.07
    oot
    0.07
     representation
    0.07
     Dual
    0.07
     elig
    0.07
     switch
    0.07
     natural
    0.07
    Activations Density 0.005%

    No Known Activations