© 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. 116900
    Prev
    Next
    INDEX
    Explanations

    significant architectural landmarks and structures

    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
     Colombian
    -0.08
    ovich
    -0.08
    meni
    -0.07
    kos
    -0.06
     Ukrainian
    -0.06
     Croatian
    -0.06
     eskort
    -0.06
    ylvania
    -0.06
    ÅĽcie
    -0.06
     Robbins
    -0.06
    POSITIVE LOGITS
    .dk
    0.13
     Copenhagen
    0.12
     Denmark
    0.11
     Danish
    0.11
     Nielsen
    0.11
     Zealand
    0.10
    strup
    0.10
    alborg
    0.10
    ø
    0.10
     Greenland
    0.09
    Activations Density 0.050%

    No Known Activations