© 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. 27925
    Prev
    Next
    INDEX
    Explanations

    elements related to layout and user interface structure in programming contexts

    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
    illas
    -0.07
    icari
    -0.06
    oucher
    -0.06
    akt
    -0.06
    eti
    -0.06
    meaning
    -0.06
    Ä°T
    -0.06
    olon
    -0.06
     SaÄŁ
    -0.06
    illion
    -0.06
    POSITIVE LOGITS
     McConnell
    0.07
    Suppress
    0.06
     PAD
    0.06
     Spiritual
    0.06
    sky
    0.06
    thora
    0.06
    antz
    0.06
     proport
    0.06
    ãĥ¼ãĤ¹
    0.06
    dorf
    0.06
    Activations Density 0.000%

    No Known Activations