© 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. 15-LLAMASCOPE-RES-131K
    11. 26703
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate permission, rights, or commitments

    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
    elyn
    -0.06
     del
    -0.06
     either
    -0.06
     Blues
    -0.06
    /to
    -0.06
     Bros
    -0.06
    lem
    -0.06
     Bills
    -0.06
    oul
    -0.05
    avers
    -0.05
    POSITIVE LOGITS
    Å¡et
    0.07
    ovny
    0.07
     تا
    0.07
    pler
    0.07
    arrant
    0.07
    VILLE
    0.06
     ÅĻÃŃj
    0.06
    sville
    0.06
    *)((
    0.06
    562
    0.06
    Activations Density 0.009%

    No Known Activations