© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 126161
    Prev
    Next
    INDEX
    Explanations

    phrases indicating preparation for an event or action

    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
    ifu
    -0.08
    uter
    -0.07
    andi
    -0.07
     اÙĦرÙħزÙĬØ©
    -0.07
    aight
    -0.07
    orsi
    -0.07
     ncols
    -0.07
    ousing
    -0.07
    agit
    -0.06
    gua
    -0.06
    POSITIVE LOGITS
     exit
    0.07
     preparation
    0.07
     PIPE
    0.06
     Company
    0.06
     prepar
    0.06
     internal
    0.06
     preparing
    0.06
     Exit
    0.06
     Internal
    0.06
     company
    0.06
    Activations Density 0.000%

    No Known Activations