© 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. 22-LLAMASCOPE-RES-131K
    11. 4131
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols

    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
     Sort
    -0.07
    Sort
    -0.07
    	Copyright
    -0.07
    iani
    -0.07
    gratis
    -0.07
     Sawyer
    -0.06
     '{@
    -0.06
     Rencontre
    -0.06
    .tm
    -0.06
    mys
    -0.06
    POSITIVE LOGITS
     elim
    0.08
     Elim
    0.08
     therefore
    0.07
     solving
    0.07
    then
    0.07
     solved
    0.06
     then
    0.06
     Now
    0.06
     elimin
    0.06
    à¸ĩà¸Ļ
    0.06
    Activations Density 0.047%

    No Known Activations