© 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. 71415
    Prev
    Next
    INDEX
    Explanations

    words related to legal and regulatory concerns

    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
    ilece
    -0.07
    toJson
    -0.07
    --+
    -0.06
     Nicholson
    -0.06
    riba
    -0.06
     musel
    -0.06
    otros
    -0.06
    erator
    -0.06
     بÙĪابة
    -0.06
    eum
    -0.06
    POSITIVE LOGITS
     thereof
    0.13
     alike
    0.10
    allis
    0.06
     respectively
    0.05
    ange
    0.05
     Hir
    0.05
    Æ¡i
    0.05
    ãģĿãĤĮ
    0.05
    λÏİ
    0.05
    ole
    0.05
    Activations Density 0.067%

    No Known Activations