© 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. 82569
    Prev
    Next
    INDEX
    Explanations

    phrases indicating success or acclaim in creative works, particularly in entertainment

    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
     recent
    -0.09
     recently
    -0.08
     Recently
    -0.08
     lately
    -0.08
    recent
    -0.07
    Recently
    -0.07
     latest
    -0.07
     ìµľê·¼
    -0.07
     yesterday
    -0.06
    pector
    -0.06
    POSITIVE LOGITS
     ëĭ¹ìĭľ
    0.10
     tehdy
    0.07
    åĿĬ
    0.07
    revolution
    0.07
    utos
    0.07
    was
    0.07
    第ä¸Ģ次
    0.06
    lav
    0.06
    were
    0.06
    toi
    0.06
    Activations Density 0.009%

    No Known Activations