© 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. 129224
    Prev
    Next
    INDEX
    Explanations

    topics related to historical and social issues, particularly involving humanitarian concerns and their implications

    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
    ron
    -0.06
     academia
    -0.06
    VML
    -0.06
    ¸ı
    -0.05
    .STATUS
    -0.05
     cot
    -0.05
     everything
    -0.05
    antine
    -0.05
     inconvenient
    -0.05
     inconsist
    -0.05
    POSITIVE LOGITS
    ลาà¸Ķ
    0.08
    _vlog
    0.07
    ORIZ
    0.07
    iji
    0.07
    ırak
    0.07
    .HandlerFunc
    0.07
    ixin
    0.07
    anches
    0.07
    imbus
    0.07
    dıģında
    0.07
    Activations Density 0.001%

    No Known Activations