© 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 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. 83018
    Prev
    Next
    INDEX
    Explanations

    references to editions and updates of artistic or literary works

    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
    оÑĢаз
    -0.07
    moz
    -0.06
    orst
    -0.05
    Editable
    -0.05
    ijkstra
    -0.05
    uplicates
    -0.05
     eyed
    -0.05
    _eye
    -0.05
    vary
    -0.05
     Fetish
    -0.05
    POSITIVE LOGITS
     updates
    0.11
     Updates
    0.10
    updates
    0.10
    Updates
    0.10
    :update
    0.10
    æĸ°å¢ŀ
    0.09
     update
    0.09
    _updates
    0.09
     aggi
    0.09
     Update
    0.09
    Activations Density 0.009%

    No Known Activations