© 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. 75728
    Prev
    Next
    INDEX
    Explanations

    actions and processes related to execution and implementation

    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
    roker
    -0.08
     çī
    -0.08
    theid
    -0.07
    weg
    -0.07
     Linh
    -0.07
    istrov
    -0.07
    æŀĿ
    -0.07
    classnames
    -0.07
    ãĤªãĥª
    -0.07
    edom
    -0.07
    POSITIVE LOGITS
     plan
    0.08
     policies
    0.07
     plans
    0.07
     schemes
    0.07
     strategies
    0.07
     strategy
    0.07
    plan
    0.07
     pena
    0.06
     transactions
    0.06
     vengeance
    0.06
    Activations Density 0.028%

    No Known Activations