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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 127916
    Prev
    Next
    INDEX
    Explanations

    references to personal identification or ownership of web domains

    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
    poll
    -0.08
    ogy
    -0.07
    ibName
    -0.07
    Ranked
    -0.07
    ngle
    -0.07
    IClient
    -0.07
    aria
    -0.07
     ÐŀÑģоб
    -0.07
    strict
    -0.07
    vie
    -0.06
    POSITIVE LOGITS
     address
    0.08
     listed
    0.07
     same
    0.07
     website
    0.07
     telephone
    0.06
    listed
    0.06
     nothing
    0.06
     domain
    0.06
     registr
    0.06
     domains
    0.06
    Activations Density 0.008%

    No Known Activations