© 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. 85761
    Prev
    Next
    INDEX
    Explanations

    instances of military context or terminology

    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
    ayout
    -0.07
    isi
    -0.06
     jos
    -0.06
    bone
    -0.06
    Cache
    -0.06
    itzer
    -0.06
    æı
    -0.06
    Arrow
    -0.06
    Unc
    -0.05
    ÄĽÅĻ
    -0.05
    POSITIVE LOGITS
    eks
    0.07
    anh
    0.07
    ãĥ«ãĤ¯
    0.06
    itti
    0.06
    antaged
    0.06
    ειο
    0.06
    ekk
    0.06
    _CTX
    0.06
    .bp
    0.06
    ek
    0.06
    Activations Density 0.002%

    No Known Activations