© 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. 70239
    Prev
    Next
    INDEX
    Explanations

    technical terms and symbols related to signal processing and digital communication

    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
    rex
    -0.06
    enaire
    -0.06
    pone
    -0.06
    west
    -0.06
    ).(
    -0.06
    asl
    -0.05
    aminer
    -0.05
     sine
    -0.05
     press
    -0.05
    asset
    -0.05
    POSITIVE LOGITS
    aub
    0.07
     queryInterface
    0.07
    uentes
    0.07
    ør
    0.07
    raÄį
    0.07
     (
    0.06
    óÅĤ
    0.06
    rá
    0.06
    owe
    0.06
     ActionTypes
    0.06
    Activations Density 0.082%

    No Known Activations