© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 59791
    Prev
    Next
    INDEX
    Explanations

    phrases related to military organization and structure

    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
    isser
    -0.07
    amak
    -0.06
    iar
    -0.06
    \OptionsResolver
    -0.06
     Hutch
    -0.06
    enstein
    -0.06
     Roc
    -0.06
    untu
    -0.06
    ibur
    -0.06
    ær
    -0.06
    POSITIVE LOGITS
     trang
    0.08
    izons
    0.07
    agua
    0.07
    ÐļТ
    0.07
    units
    0.07
    323
    0.06
    翼
    0.06
    Formation
    0.06
    548
    0.06
    iskey
    0.06
    Activations Density 0.017%

    No Known Activations