© 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. 61482
    Prev
    Next
    INDEX
    Explanations

    actions and moments related to sports gameplay

    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
    holm
    -0.07
    ¶Į
    -0.07
    ucz
    -0.07
    skou
    -0.07
     osc
    -0.07
    ellas
    -0.07
    ACHER
    -0.07
    ãĥ¬ãĤ¹
    -0.06
    .deck
    -0.06
    agma
    -0.06
    POSITIVE LOGITS
     isolated
    0.08
    ingo
    0.07
    argin
    0.06
    isol
    0.06
    ré
    0.06
     elect
    0.06
     solo
    0.06
    äºĮ人
    0.06
     lone
    0.06
    kili
    0.06
    Activations Density 0.015%

    No Known Activations