© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 104035
    Prev
    Next
    INDEX
    Explanations

    instances of people engaging in social or political actions

    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
    جÛĮ
    -0.08
    ivent
    -0.07
    iasm
    -0.07
    ported
    -0.07
    ÐļÐĺ
    -0.07
    оваÑĢ
    -0.07
    ugins
    -0.07
    á»ijt
    -0.07
     getenv
    -0.07
    анÑģи
    -0.07
    POSITIVE LOGITS
     peacefully
    0.06
     innoc
    0.06
     toler
    0.06
     harmless
    0.06
     slightly
    0.06
     allegedly
    0.06
     sparing
    0.06
    onth
    0.06
     Sanchez
    0.05
    onte
    0.05
    Activations Density 0.018%

    No Known Activations