© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3997
    Prev
    Next
    INDEX
    Explanations

    references to programming components and libraries

    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
    صØŃ
    -0.07
    rana
    -0.07
    artner
    -0.07
    riba
    -0.07
    undy
    -0.06
    piel
    -0.06
    ãĥł
    -0.06
     Jarvis
    -0.06
    ulado
    -0.06
     Duis
    -0.06
    POSITIVE LOGITS
    OSC
    0.06
    inator
    0.06
    .lv
    0.06
    iser
    0.06
    bose
    0.06
    ager
    0.06
     utility
    0.06
     library
    0.06
     package
    0.06
    inate
    0.06
    Activations Density 0.072%

    No Known Activations