© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 31233
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "BeSpacific" and its variations, highlighting its relevance in legal and information contexts

    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
    uchen
    -0.06
    ropy
    -0.06
    impan
    -0.06
    ogy
    -0.06
     Facilities
    -0.06
    ual
    -0.06
    uche
    -0.06
    .percent
    -0.06
    âĢ¦↵↵
    -0.06
    óg
    -0.06
    POSITIVE LOGITS
    elier
    0.07
    isten
    0.07
    aaS
    0.07
    ijn
    0.07
    Unc
    0.07
     INTERRUPTION
    0.07
    eways
    0.07
    emailer
    0.07
     DISCLAIM
    0.07
     <=>
    0.07
    Activations Density 0.028%

    No Known Activations