© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 98551
    Prev
    Next
    INDEX
    Explanations

    terms related to authorship and publication

    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
    jang
    -0.07
    lass
    -0.07
    ermal
    -0.07
    .Tween
    -0.06
    ipp
    -0.06
    atal
    -0.06
     un
    -0.06
    rer
    -0.06
     JsonSerializer
    -0.06
    umann
    -0.06
    POSITIVE LOGITS
    ItemAt
    0.06
    APS
    0.06
     jenter
    0.06
    Naming
    0.06
     Leah
    0.06
    ãĥ³ãĤº
    0.06
    ght
    0.06
    èĮĥ
    0.06
    lain
    0.06
    .Sdk
    0.06
    Activations Density 0.001%

    No Known Activations