© 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. 84467
    Prev
    Next
    INDEX
    Explanations

    references to governmental processes and regulations

    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
    ½æķ°
    -0.07
    MASK
    -0.06
    ums
    -0.06
    amak
    -0.06
    _verbose
    -0.06
    istine
    -0.06
    .orange
    -0.06
    TEE
    -0.06
    CodeGen
    -0.06
    ÄĽ
    -0.06
    POSITIVE LOGITS
     Border
    0.11
     Customs
    0.10
     Immigration
    0.10
    Border
    0.10
     border
    0.09
     immigration
    0.09
     BORDER
    0.08
    (border
    0.08
     smuggling
    0.08
    border
    0.08
    Activations Density 0.004%

    No Known Activations