© 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. 57470
    Prev
    Next
    INDEX
    Explanations

    titles and roles related to academic and organizational positions

    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
    alyzer
    -0.07
     ÎĶε
    -0.06
     Representatives
    -0.06
     Ãĸl
    -0.06
     док
    -0.06
    oren
    -0.06
    ExecutionContext
    -0.06
    gis
    -0.06
    iser
    -0.06
    pecia
    -0.06
    POSITIVE LOGITS
    unker
    0.07
    ãĥ¼ãĥĹ
    0.07
     Bom
    0.06
    owi
    0.06
    ÑĢÑĥп
    0.06
    ãĥ¼ãĥŀ
    0.06
     affairs
    0.06
    acio
    0.06
    rani
    0.06
    idd
    0.06
    Activations Density 0.015%

    No Known Activations