© 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. 29943
    Prev
    Next
    INDEX
    Explanations

    references to dance and military tributes

    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
     конÑĦеÑĢен
    -0.07
    å¹¹ç·ļ
    -0.07
     architekt
    -0.07
    ãĤ¨ãĥ«
    -0.07
    ê·
    -0.07
    ARGIN
    -0.07
     Pilot
    -0.07
    >(*
    -0.07
    geries
    -0.07
    еÑĢп
    -0.07
    POSITIVE LOGITS
     performed
    0.09
     perform
    0.08
     performance
    0.07
     performances
    0.07
     performs
    0.07
     pomp
    0.06
     dance
    0.06
    Performed
    0.06
     parade
    0.06
     marching
    0.06
    Activations Density 0.160%

    No Known Activations