© 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. 94193
    Prev
    Next
    INDEX
    Explanations

    concepts related to product development and management processes

    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
    IRS
    -0.07
    åħ¬å¼ı
    -0.07
    wrapped
    -0.07
    plr
    -0.07
    oms
    -0.07
    ettes
    -0.07
     Kür
    -0.07
     Affero
    -0.06
    lg
    -0.06
    neutral
    -0.06
    POSITIVE LOGITS
     design
    0.10
     Design
    0.10
    Design
    0.09
     designs
    0.09
     Designs
    0.08
    íĴĪ
    0.08
     designers
    0.08
     manufact
    0.08
     production
    0.07
     Production
    0.07
    Activations Density 0.010%

    No Known Activations