© 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. 106834
    Prev
    Next
    INDEX
    Explanations

    instances of drawing and artistic creation

    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
    iment
    -0.06
    shot
    -0.06
    stant
    -0.06
    ='{$
    -0.06
     Hol
    -0.06
    theless
    -0.06
    hol
    -0.06
     Edge
    -0.05
     photography
    -0.05
     viewing
    -0.05
    POSITIVE LOGITS
     drawn
    0.08
    ản
    0.07
     drew
    0.07
    ohana
    0.06
    ONSE
    0.06
    INGER
    0.06
    REDIS
    0.06
    ouri
    0.06
    ooter
    0.06
     Draws
    0.06
    Activations Density 0.021%

    No Known Activations