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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 83110
    Prev
    Next
    INDEX
    Explanations

    the various forms of the verb "know."

    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
    elu
    -0.07
    мена
    -0.06
     Cs
    -0.06
     docking
    -0.06
    маÑħ
    -0.06
    ãĥķãĤ
    -0.06
    лаб
    -0.06
    icont
    -0.06
    reta
    -0.06
    ÏģοÏĤ
    -0.06
    POSITIVE LOGITS
    349
    0.07
    icker
    0.07
    nger
    0.06
    iversit
    0.06
    LC
    0.06
     copp
    0.06
    ³
    0.06
    340
    0.06
    ayet
    0.06
    iminal
    0.06
    Activations Density 0.009%

    No Known Activations