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. 22-LLAMASCOPE-RES-131K
    6. 5202
    Prev
    Next
    INDEX
    Explanations

    mentions of video animation and related skills

    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
    ä¸ĸç´Ģ
    -0.08
    blur
    -0.07
    -regexp
    -0.07
    ạc
    -0.07
    ãĥ¼ãĥĭ
    -0.07
    é¨
    -0.07
    lfw
    -0.07
    à¸łà¸²à¸ŀ
    -0.07
     photographs
    -0.07
     photographers
    -0.07
    POSITIVE LOGITS
     animation
    0.10
     animated
    0.10
     Animated
    0.09
     anim
    0.09
     expl
    0.09
     animations
    0.09
     Animation
    0.09
     Motion
    0.09
     motion
    0.09
     Anim
    0.08
    Activations Density 0.004%

    No Known Activations