© 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. 118313
    Prev
    Next
    INDEX
    Explanations

    specific rules and guidelines related to gaming or gaming scenarios

    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
     Wenger
    -0.07
    robe
    -0.06
    ruba
    -0.06
    ekl
    -0.06
     Bars
    -0.06
     instrument
    -0.06
    angers
    -0.06
     ziy
    -0.06
     eth
    -0.06
     bfd
    -0.06
    POSITIVE LOGITS
    ocha
    0.07
    boarding
    0.07
     Conv
    0.07
    Conv
    0.07
    Hex
    0.07
     Hobby
    0.07
    CustomAttributes
    0.07
    isor
    0.06
     erotici
    0.06
    ible
    0.06
    Activations Density 0.036%

    No Known Activations