© 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. 93412
    Prev
    Next
    INDEX
    Explanations

    directives and instructions related to military or organizational operations

    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
     createSelector
    -0.07
    SetFont
    -0.06
    rai
    -0.06
    ecta
    -0.06
    rava
    -0.06
    æı
    -0.06
    unan
    -0.06
    okt
    -0.06
    Montserrat
    -0.06
    /rfc
    -0.06
    POSITIVE LOGITS
     instructions
    0.13
     instructed
    0.12
     instruction
    0.11
     Instructions
    0.10
    Instructions
    0.09
    Instruction
    0.09
     instruct
    0.08
    instructions
    0.08
    instruction
    0.08
     tasks
    0.08
    Activations Density 0.064%

    No Known Activations