© 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. 40468
    Prev
    Next
    INDEX
    Explanations

    trends and patterns in population and cultural changes over time

    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
    oler
    -0.09
     doubling
    -0.08
    .mit
    -0.08
    iffies
    -0.08
    oltip
    -0.08
    forman
    -0.08
    ^[
    -0.08
    upertino
    -0.07
    rrha
    -0.07
    \Bridge
    -0.07
    POSITIVE LOGITS
     decline
    0.18
     declining
    0.15
     declines
    0.14
     declined
    0.13
    decl
    0.12
    Decl
    0.12
     decreasing
    0.11
     Decl
    0.11
     decrease
    0.11
     dwind
    0.11
    Activations Density 0.216%

    No Known Activations