© 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. 15-LLAMASCOPE-RES-131K
    11. 86475
    Prev
    Next
    INDEX
    Explanations

    expressions related to geopolitics and power 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
     Snap
    -0.07
    anca
    -0.07
    arf
    -0.07
    enstein
    -0.07
    pectives
    -0.06
    rei
    -0.06
    allet
    -0.06
     stamp
    -0.06
     Skip
    -0.06
    azel
    -0.06
    POSITIVE LOGITS
    ulner
    0.07
     vulnerability
    0.07
     دÙģ
    0.06
     güvenlik
    0.06
    /WebAPI
    0.06
     External
    0.06
    亡
    0.06
     humili
    0.06
    ãĥĹãĥ¬
    0.06
     Guard
    0.06
    Activations Density 0.030%

    No Known Activations