© 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. 15-LLAMASCOPE-RES-131K
    11. 89805
    Prev
    Next
    INDEX
    Explanations

    possessive constructions in the text

    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
    eam
    -0.07
    oque
    -0.07
     sibling
    -0.06
    [email
    -0.06
    Sibling
    -0.06
     пеÑĢек
    -0.06
    å®®
    -0.06
    olib
    -0.06
    itest
    -0.06
     possibility
    -0.06
    POSITIVE LOGITS
     personal
    0.09
     own
    0.09
    /her
    0.08
    personal
    0.08
     personally
    0.08
     himself
    0.08
    bage
    0.07
    rtle
    0.07
    енÑĮ
    0.07
    sing
    0.07
    Activations Density 0.049%

    No Known Activations