© 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. 4361
    Prev
    Next
    INDEX
    Explanations

    structured educational content and instructional guidance

    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
    uga
    -0.07
     Ages
    -0.06
     Records
    -0.06
    ulumi
    -0.06
    Records
    -0.06
    tie
    -0.06
    sted
    -0.06
    опÑĢи
    -0.06
    agers
    -0.06
     records
    -0.06
    POSITIVE LOGITS
     level
    0.14
     Level
    0.12
    level
    0.12
    _level
    0.11
    Level
    0.11
     levels
    0.10
     LEVEL
    0.10
    .level
    0.10
    LEVEL
    0.10
     niveau
    0.10
    Activations Density 0.011%

    No Known Activations