© 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. 90509
    Prev
    Next
    INDEX
    Explanations

    instances of player names and team affiliations 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
    nik
    -0.07
    áce
    -0.07
    CEED
    -0.07
    umbed
    -0.07
    acades
    -0.07
    anyl
    -0.07
    ogan
    -0.07
    abeth
    -0.07
    others
    -0.07
    ogne
    -0.06
    POSITIVE LOGITS
     previously
    0.06
     last
    0.06
     twice
    0.06
    ÏĦÏī
    0.06
     came
    0.06
    spar
    0.06
    _STRIP
    0.06
     emph
    0.06
    .gwt
    0.06
     earlier
    0.06
    Activations Density 0.011%

    No Known Activations