© 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. 87600
    Prev
    Next
    INDEX
    Explanations

    references to organizational structures and processes related to cost estimation and acquisition policies

    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
    jes
    -0.06
     Hospitality
    -0.06
    ilde
    -0.06
    OVÃģ
    -0.06
    âĢ¦↵
    -0.06
     Kür
    -0.05
    amic
    -0.05
    主任
    -0.05
     cap
    -0.05
     bang
    -0.05
    POSITIVE LOGITS
    -wide
    0.16
    wide
    0.14
     wide
    0.11
    Wide
    0.10
     Wide
    0.10
     widest
    0.08
     wider
    0.08
    -standard
    0.08
     Internal
    0.08
    ẽ
    0.07
    Activations Density 0.033%

    No Known Activations