© 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. 84649
    Prev
    Next
    INDEX
    Explanations

    phrases related to document formatting and images

    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
    ttp
    -0.07
     avent
    -0.07
     Ðĵолов
    -0.06
    ascus
    -0.06
    enso
    -0.06
    .hex
    -0.06
     Fur
    -0.06
    AFE
    -0.06
    à¥ĩव
    -0.06
    串
    -0.06
    POSITIVE LOGITS
     table
    0.11
     figure
    0.11
     caption
    0.10
    figure
    0.09
     tables
    0.09
     image
    0.09
    (table
    0.08
    table
    0.08
     Figure
    0.08
     Table
    0.08
    Activations Density 0.233%

    No Known Activations