© 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. 62072
    Prev
    Next
    INDEX
    Explanations

    references to specific geopolitical entities and terms related to significant current events or organizations

    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
    _EXTENSIONS
    -0.08
    -packages
    -0.07
    >null
    -0.07
    ::::::::::::::::::::::::::::::::
    -0.07
    odelist
    -0.07
    ãĤ¥
    -0.07
    &gt
    -0.07
    eam
    -0.07
    abox
    -0.06
    [email
    -0.06
    POSITIVE LOGITS
    anos
    0.06
     lou
    0.06
    andal
    0.06
    виÑĤ
    0.06
    anson
    0.06
    iet
    0.06
    ican
    0.06
     proper
    0.06
    icens
    0.06
    andra
    0.06
    Activations Density 0.029%

    No Known Activations