© 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. 15-LLAMASCOPE-RES-131K
    11. 90069
    Prev
    Next
    INDEX
    Explanations

    names of countries and associated geographical terms

    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
    oy
    -0.07
    wright
    -0.07
    oda
    -0.06
    estr
    -0.06
    uffman
    -0.06
    veau
    -0.06
     Welch
    -0.06
    .dk
    -0.06
     dicks
    -0.06
    Bu
    -0.06
    POSITIVE LOGITS
    ddit
    0.09
    #ad
    0.07
    ruba
    0.07
    #ab
    0.07
     Aires
    0.07
     Hava
    0.07
     Coco
    0.06
    (AT
    0.06
    .obs
    0.06
    #ac
    0.06
    Activations Density 0.044%

    No Known Activations