© 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 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. 87354
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and related expressions indicating ownership or belonging

    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
    fab
    -0.07
    HeaderCode
    -0.06
    indre
    -0.06
    ahl
    -0.06
    nee
    -0.06
    leep
    -0.06
     bekl
    -0.06
    sage
    -0.06
    createCommand
    -0.06
     Flowers
    -0.06
    POSITIVE LOGITS
    anio
    0.07
    sing
    0.06
     protagonists
    0.06
    imum
    0.06
    ¹
    0.06
     mktime
    0.06
     organism
    0.06
    inea
    0.06
    ainter
    0.06
     Nem
    0.06
    Activations Density 0.074%

    No Known Activations