© 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. 119826
    Prev
    Next
    INDEX
    Explanations

    JSON or structured data-related elements in the text

    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
    893
    -0.07
    BuilderFactory
    -0.07
    794
    -0.06
    671
    -0.06
    887
    -0.06
    /release
    -0.06
    ToF
    -0.06
    onec
    -0.06
    Det
    -0.06
    /core
    -0.06
    POSITIVE LOGITS
     defaultValue
    0.07
     default
    0.07
    defaultValue
    0.07
    .setter
    0.07
    NullException
    0.06
    irim
    0.06
    azer
    0.06
    owell
    0.06
    .datab
    0.06
     constrained
    0.06
    Activations Density 0.080%

    No Known Activations