© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 106546
    Prev
    Next
    INDEX
    Explanations

    instances where "pay" or "paying attention" is mentioned

    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
    anka
    -0.08
    MN
    -0.07
    ILED
    -0.07
     æ¿
    -0.07
    chen
    -0.07
    plex
    -0.07
    redicate
    -0.07
    ogl
    -0.06
    rip
    -0.06
    ouz
    -0.06
    POSITIVE LOGITS
    ırak
    0.07
    skirts
    0.07
     closely
    0.07
     carefully
    0.07
    OWL
    0.06
    459
    0.06
    agus
    0.06
    789
    0.06
    oulouse
    0.06
     attent
    0.06
    Activations Density 0.004%

    No Known Activations