© 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 EvalsExportsinterp-engineNEWAPI 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. 27427
    Prev
    Next
    INDEX
    Explanations

    references to ongoing discussions about international crises and their impact on Central African political dynamics

    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
    illum
    -0.07
    ãĤ
    -0.07
    nika
    -0.06
     Už
    -0.06
     Newspaper
    -0.06
    ITERAL
    -0.06
    pras
    -0.06
    itched
    -0.06
    chter
    -0.06
    zzle
    -0.06
    POSITIVE LOGITS
    eeper
    0.06
    rig
    0.06
     spoilers
    0.06
     yourselves
    0.06
     marque
    0.06
    Mocks
    0.06
    de
    0.06
    çł²
    0.06
    urar
    0.06
    ClientRect
    0.06
    Activations Density 0.005%

    No Known Activations