© 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. 40790
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the significance or affordability of something

    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
    ordan
    -0.07
    reas
    -0.07
     zwar
    -0.07
    ÏĥÏĦε
    -0.06
    ake
    -0.06
     sice
    -0.06
    ord
    -0.06
    ายà¸Ļ
    -0.06
    ео
    -0.06
    -php
    -0.06
    POSITIVE LOGITS
    tery
    0.08
     also
    0.08
    tera
    0.07
    -ÑĤо
    0.07
     underlying
    0.07
    also
    0.07
     nonetheless
    0.06
     certainly
    0.06
     Also
    0.06
    tes
    0.06
    Activations Density 0.033%

    No Known Activations