© 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. 94120
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating leadership qualities and proactive decision-making

    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
    ç«ĭãģ¦
    -0.06
    argas
    -0.06
    otte
    -0.06
     Alerts
    -0.06
    ìĸ¼
    -0.06
    ála
    -0.06
    omba
    -0.06
    rane
    -0.06
    reh
    -0.06
    jav
    -0.06
    POSITIVE LOGITS
     advantage
    0.09
     steps
    0.09
    steps
    0.08
     liberties
    0.08
     Steps
    0.07
    .Typed
    0.07
    uchi
    0.07
     stance
    0.07
    Steps
    0.07
    ownership
    0.07
    Activations Density 0.018%

    No Known Activations