© 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. 9-LLAMASCOPE-RES-131K
    11. 94217
    Prev
    Next
    INDEX
    Explanations

    possessive forms indicating ownership

    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
    annes
    -0.07
    ish
    -0.07
    èĢħçļĦ
    -0.06
    innamon
    -0.06
     Sawyer
    -0.06
     altogether
    -0.06
    439
    -0.06
    овани
    -0.06
    imm
    -0.06
    ediator
    -0.06
    POSITIVE LOGITS
    ureau
    0.09
    agine
    0.08
    ãģĿãĤĮãģ¯
    0.07
    DMI
    0.07
    raison
    0.07
    uhl
    0.07
    entai
    0.06
     aks
    0.06
    кÑĤÑĥ
    0.06
    /cms
    0.06
    Activations Density 0.050%

    No Known Activations