Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 128913
    Prev
    Next
    INDEX
    Explanations

    phrases involving the word "given" in various contexts, often indicating permissions, responsibilities, or assignments

    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
     mé
    -0.07
    cht
    -0.06
    lege
    -0.06
    eba
    -0.06
    üt
    -0.06
     Tooth
    -0.06
    arse
    -0.06
    118
    -0.06
     æ¢
    -0.06
    roups
    -0.06
    POSITIVE LOGITS
     tasks
    0.08
     opportunity
    0.07
    keys
    0.07
    æĻ´
    0.07
    Communic
    0.07
    ÑĤик
    0.07
    ä»»åĬ¡
    0.07
     marching
    0.07
     Communic
    0.06
    gift
    0.06
    Activations Density 0.029%

    No Known Activations