© 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. 88388
    Prev
    Next
    INDEX
    Explanations

    references to legislative proposals and discussions in a political context

    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
    chten
    -0.07
    npos
    -0.07
    embed
    -0.07
    меÑĩ
    -0.07
    reach
    -0.07
    arus
    -0.07
    vell
    -0.07
    <boost
    -0.07
    Specifier
    -0.07
     eldre
    -0.07
    POSITIVE LOGITS
     motion
    0.06
     session
    0.06
    ungan
    0.06
    /simple
    0.06
     Bracket
    0.05
     Cic
    0.05
     disfr
    0.05
     spoke
    0.05
     basket
    0.05
     Tam
    0.05
    Activations Density 0.003%

    No Known Activations