© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 62330
    Prev
    Next
    INDEX
    Explanations

    references to legal or formal processes involving migration and marriage

    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
    аÑĢод
    -0.09
    icense
    -0.08
    bjerg
    -0.07
     brands
    -0.07
    enn
    -0.07
    -shift
    -0.07
    ढ
    -0.07
    linger
    -0.07
    shift
    -0.07
     меÑĢе
    -0.07
    POSITIVE LOGITS
     relative
    0.06
    INDER
    0.06
     paren
    0.06
     waited
    0.06
    å¾ħ
    0.06
    ozem
    0.06
     conj
    0.06
     завеÑĢ
    0.06
    Ĥ
    0.05
    indr
    0.05
    Activations Density 0.002%

    No Known Activations