Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95879
    Prev
    Next
    INDEX
    Explanations

    phrases indicating urgency or lack of clarity in communication

    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
    ÙĪÛĮÙĩ
    -0.06
    iê
    -0.06
    aca
    -0.06
     Economy
    -0.06
    bir
    -0.06
    610
    -0.05
    rss
    -0.05
    oya
    -0.05
    az
    -0.05
     
    -0.05
    POSITIVE LOGITS
    duk
    0.08
    dÃŃ
    0.07
     Blades
    0.07
    =length
    0.07
    athi
    0.07
    hud
    0.07
    uhn
    0.07
    enor
    0.07
    ableView
    0.07
    aneously
    0.07
    Activations Density 0.002%

    No Known Activations