© 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. 22-LLAMASCOPE-RES-131K
    11. 4190
    Prev
    Next
    INDEX
    Explanations

    elements related to events or competitions

    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
    á»ı
    -0.06
     DESC
    -0.06
     QLD
    -0.06
     Congressional
    -0.05
    _HTTP
    -0.05
    âĢķ
    -0.05
    admins
    -0.05
    guards
    -0.05
    лем
    -0.05
     Genre
    -0.05
    POSITIVE LOGITS
     column
    0.09
     reader
    0.09
     columns
    0.09
     columnist
    0.09
     Column
    0.09
     readers
    0.08
    COLUMN
    0.08
    column
    0.08
     COLUMN
    0.08
    Column
    0.08
    Activations Density 0.087%

    No Known Activations