© 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 EvalsExportsinterp-engineNEWAPI 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. 95194
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and related terms 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
    scala
    -0.07
    illes
    -0.07
    ying
    -0.07
    onet
    -0.07
    rary
    -0.07
    (æľ¨
    -0.07
    ëĵĿ
    -0.06
    dete
    -0.06
    eldon
    -0.06
    ">//
    -0.06
    POSITIVE LOGITS
    aggable
    0.06
    amedi
    0.06
    wright
    0.06
     behalf
    0.06
    amed
    0.06
    UNDLE
    0.05
     territory
    0.05
     Wright
    0.05
    .son
    0.05
     incoming
    0.05
    Activations Density 0.043%

    No Known Activations