© 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. 9-LLAMASCOPE-RES-131K
    11. 95631
    Prev
    Next
    INDEX
    Explanations

    terms related to DNS (Domain Name System) and server configurations

    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
    ummer
    -0.08
    nowrap
    -0.07
    jspx
    -0.07
    ienen
    -0.07
    arget
    -0.07
    ardin
    -0.07
    engin
    -0.07
    oard
    -0.07
    hl
    -0.07
    füh
    -0.07
    POSITIVE LOGITS
    leigh
    0.06
    101
    0.06
     Bread
    0.06
    0.06
     stresses
    0.06
    adv
    0.05
     bread
    0.05
    Translated
    0.05
    blade
    0.05
     Comple
    0.05
    Activations Density 0.001%

    No Known Activations