© 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. 106144
    Prev
    Next
    INDEX
    Explanations

    terms related to government and military organizations

    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
     Heath
    -0.07
    Occurred
    -0.06
     lean
    -0.06
     Mand
    -0.06
    emean
    -0.06
    jet
    -0.06
     Lean
    -0.06
     cath
    -0.06
     Ave
    -0.06
     ave
    -0.06
    POSITIVE LOGITS
     dav
    0.07
    enez
    0.07
     GPL
    0.07
     IPT
    0.07
    лÑİÑĩа
    0.07
    Stick
    0.07
     âĸ³
    0.07
    cilik
    0.07
    aclass
    0.07
    ục
    0.07
    Activations Density 0.001%

    No Known Activations