© 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. 14813
    Prev
    Next
    INDEX
    Explanations

    occurrences of military or engineering-related terms

    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
    anel
    -0.06
    kur
    -0.06
    abb
    -0.06
    atu
    -0.06
     cont
    -0.06
    que
    -0.06
     token
    -0.06
    incer
    -0.06
    ados
    -0.05
    zech
    -0.05
    POSITIVE LOGITS
    lander
    0.08
    ityEngine
    0.07
    ↵↵
    0.07
    apor
    0.07
    æĬĺ
    0.07
    OMIC
    0.06
    +-+-
    0.06
     ÑĦÑĥнда
    0.06
     kå
    0.06
    aeper
    0.06
    Activations Density 0.049%

    No Known Activations