© 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. 81320
    Prev
    Next
    INDEX
    Explanations

    references to technology and technical processes

    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
    strup
    -0.08
    ÑŁ
    -0.08
    /pkg
    -0.07
    uilder
    -0.07
    âĻª↵↵
    -0.07
    οÏħλ
    -0.07
    ancode
    -0.07
    ãĢģå°ı
    -0.07
    (and
    -0.07
    .telegram
    -0.07
    POSITIVE LOGITS
    ï¼Į並
    0.11
    ï¼Į并
    0.10
     并
    0.10
     then
    0.10
    then
    0.10
    çĦ¶åIJİ
    0.09
    ï¼ĮçĦ¶åIJİ
    0.09
    íĸĪê³ł
    0.09
    )&&
    0.09
    并
    0.08
    Activations Density 0.233%

    No Known Activations