© 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. 17-LLAMASCOPE-RES-131K
    11. 60350
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and indications of ownership

    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
    askell
    -0.07
    .override
    -0.07
    bef
    -0.07
     sama
    -0.06
    uur
    -0.06
    mae
    -0.06
    riel
    -0.06
    iswa
    -0.06
    artin
    -0.06
    оÑĢаз
    -0.06
    POSITIVE LOGITS
     sake
    0.09
    bidden
    0.07
     purposes
    0.07
    gesi
    0.07
     benefit
    0.07
    geries
    0.07
    ndern
    0.07
    508
    0.06
    Ñīие
    0.06
    rtl
    0.06
    Activations Density 0.024%

    No Known Activations