© 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 EvalsExportsinterp-engineNEWAPI 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. 41979
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals involved in sporting incidents

    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
     Cort
    -0.09
     Kansas
    -0.09
     Wichita
    -0.08
     Worce
    -0.08
    Kansas
    -0.08
     Guerrero
    -0.08
     Bristol
    -0.07
     Honda
    -0.07
     cortical
    -0.07
     Warwick
    -0.07
    POSITIVE LOGITS
     Tottenham
    0.08
    asca
    0.08
     Edmonton
    0.08
     Hampshire
    0.08
     Richmond
    0.07
     Monroe
    0.07
     Naples
    0.07
     Armenian
    0.07
     Southampton
    0.07
     Ventura
    0.07
    Activations Density 0.398%

    No Known Activations