© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 70648
    Prev
    Next
    INDEX
    Explanations

    references to nodes and components in programming or code structure

    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
     lou
    -0.07
    yaw
    -0.07
    REAM
    -0.06
     Slee
    -0.06
    ooter
    -0.06
    ãy
    -0.06
    vtk
    -0.06
     grantResults
    -0.06
    çĵľ
    -0.06
    _stride
    -0.06
    POSITIVE LOGITS
     lifes
    0.07
    ensed
    0.07
     scoring
    0.06
     score
    0.06
     viên
    0.06
     Walls
    0.06
     Fitness
    0.06
     Valent
    0.06
     fitness
    0.06
    uali
    0.06
    Activations Density 0.088%

    No Known Activations