© 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. 82223
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing ownership or possession in relation to people, places, or concepts

    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
    çĽĬ
    -0.07
    sek
    -0.07
    afs
    -0.07
    ugu
    -0.07
    avis
    -0.07
    ëĥ¥
    -0.07
     reklam
    -0.07
    _semaphore
    -0.06
    orum
    -0.06
     nackte
    -0.06
    POSITIVE LOGITS
    /core
    0.07
     core
    0.06
     every
    0.06
     efforts
    0.06
    core
    0.06
    amburger
    0.06
     why
    0.06
     effort
    0.06
     conversations
    0.06
     everything
    0.06
    Activations Density 0.014%

    No Known Activations