© 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. 71391
    Prev
    Next
    INDEX
    Explanations

    elements related to engaging and useful content for audiences

    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
    eci
    -0.07
     ek
    -0.06
     ç§
    -0.06
     positives
    -0.06
    Italic
    -0.06
    mÃŃ
    -0.06
    xn
    -0.06
    æĬ½
    -0.06
     contract
    -0.06
    urm
    -0.06
    POSITIVE LOGITS
     content
    0.08
     getContent
    0.07
     topic
    0.07
     Sesso
    0.07
     Authority
    0.07
    Authority
    0.07
     Stap
    0.07
     authority
    0.07
    -content
    0.07
     topics
    0.07
    Activations Density 0.007%

    No Known Activations