© 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. 89117
    Prev
    Next
    INDEX
    Explanations

    phrases indicating possession 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
    çĽĬ
    -0.07
     Bonds
    -0.06
    din
    -0.06
     vain
    -0.06
    ingen
    -0.06
    vironments
    -0.06
     лиÑĨ
    -0.06
    -स
    -0.05
    {}
    -0.05
    tfoot
    -0.05
    POSITIVE LOGITS
    ulla
    0.09
     possibilities
    0.08
    urre
    0.07
     possibility
    0.07
    ulton
    0.07
    etter
    0.07
     POSSIBILITY
    0.07
    asil
    0.07
    oulder
    0.06
    assi
    0.06
    Activations Density 0.046%

    No Known Activations