© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 42717
    Prev
    Next
    INDEX
    Explanations

    references to ownership or possession in a context related to services, products, or experiences

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    nut
    -0.07
    arts
    -0.06
    ãĥ¼ãĥĨãĤ£
    -0.06
    thew
    -0.06
    kos
    -0.06
    blo
    -0.06
     Herr
    -0.06
    bl
    -0.06
    (thing
    -0.06
    lette
    -0.06
    POSITIVE LOGITS
    usz
    0.07
    embros
    0.07
    ãĤ¹ãĥ¬
    0.06
    æ³Ľ
    0.06
    ëħ¼
    0.06
    oley
    0.06
    anmar
    0.06
    °
    0.06
    身ä¸Ĭ
    0.06
    ixel
    0.06
    Activations Density 0.135%

    No Known Activations