© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 83050
    Prev
    Next
    INDEX
    Explanations

    phrases related to urgency and making quick decisions

    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
    hawks
    -0.06
     Modular
    -0.06
    ãģĭãĤĬ
    -0.06
     Button
    -0.06
    slaught
    -0.06
     Jay
    -0.06
     modular
    -0.05
    enti
    -0.05
    abb
    -0.05
    ABB
    -0.05
    POSITIVE LOGITS
    asti
    0.07
    igm
    0.07
    rvé
    0.07
    apr
    0.07
    yonel
    0.07
    Ð¡Ðł
    0.07
    unicorn
    0.06
    mÃŃt
    0.06
    веÑī
    0.06
    .hasNext
    0.06
    Activations Density 0.001%

    No Known Activations