© 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. 15-LLAMASCOPE-RES-131K
    11. 87203
    Prev
    Next
    INDEX
    Explanations

    specific years and numerical data related to financial or economic performance

    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
    INCT
    -0.07
    erli
    -0.07
    maz
    -0.07
    %!
    -0.07
    eb
    -0.07
    ãĤ¯ãĥŃ
    -0.07
    Lexer
    -0.07
    EntryPoint
    -0.07
    incip
    -0.06
    .GetInstance
    -0.06
    POSITIVE LOGITS
    ugged
    0.07
    DX
    0.07
    lite
    0.06
    лад
    0.06
    liers
    0.06
    omo
    0.06
    ule
    0.05
    ellen
    0.05
    ugging
    0.05
    Lite
    0.05
    Activations Density 0.005%

    No Known Activations