© 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. 87259
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to immigration and the pursuit of a better life

    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
    emas
    -0.08
    pras
    -0.08
    arts
    -0.08
    mlink
    -0.07
    ãĥ³ãĥIJ
    -0.07
    .stringValue
    -0.07
    iyat
    -0.07
    /ws
    -0.07
    кав
    -0.07
    ngen
    -0.07
    POSITIVE LOGITS
     opportunities
    0.09
     opportunity
    0.08
     Opportunities
    0.08
     promises
    0.07
     elsewhere
    0.07
     promise
    0.07
     gre
    0.06
     Opportunity
    0.06
     promised
    0.06
     fre
    0.06
    Activations Density 0.022%

    No Known Activations