© 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 EvalsExportsinterp-engineNEWAPI 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. 73591
    Prev
    Next
    INDEX
    Explanations

    comparisons and analysis of patient data in a study

    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
    kid
    -0.06
    ãĥ¼ãĥĢ
    -0.06
    ãĤ¿ãĥ¼
    -0.06
    _kw
    -0.06
     stripes
    -0.06
    äºŃ
    -0.06
     hodin
    -0.06
    gren
    -0.06
    ·æĸ°
    -0.06
    jspx
    -0.06
    POSITIVE LOGITS
    ìķĶ
    0.07
    ÃŃo
    0.07
    rawn
    0.07
     control
    0.06
     groups
    0.06
    ãģ¾ãģĽ
    0.06
    Overall
    0.06
    both
    0.06
     Control
    0.06
     controls
    0.06
    Activations Density 0.196%

    No Known Activations