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. 5191
    Prev
    Next
    INDEX
    Explanations

    elements related to illustrations and artistic representations

    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
    sten
    -0.06
     PDF
    -0.06
    оÑĤÑĮ
    -0.06
     Lucas
    -0.05
    Showing
    -0.05
     Document
    -0.05
    .displayName
    -0.05
    è¾
    -0.05
     Volume
    -0.05
    .pdf
    -0.05
    POSITIVE LOGITS
     illustrations
    0.10
     illustrator
    0.09
     drawings
    0.08
     accompanying
    0.08
     pages
    0.08
     illustration
    0.07
     animator
    0.07
    λλη
    0.07
    ownt
    0.07
    ToProps
    0.07
    Activations Density 0.020%

    No Known Activations