© 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. 77563
    Prev
    Next
    INDEX
    Explanations

    instances of direct communication and inquiries

    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
    tempt
    -0.07
    à¸Ľà¸£à¸°à¸ª
    -0.07
    calar
    -0.07
    SAME
    -0.06
    åĺĽ
    -0.06
     bump
    -0.06
    esser
    -0.06
    gang
    -0.06
    888
    -0.06
    tement
    -0.06
    POSITIVE LOGITS
     began
    0.07
    ough
    0.07
     begin
    0.06
    384
    0.06
    .begin
    0.06
     вообÑīе
    0.06
    urma
    0.06
     arrive
    0.06
     start
    0.06
     à¤ķब
    0.06
    Activations Density 0.024%

    No Known Activations