© 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. 55313
    Prev
    Next
    INDEX
    Explanations

    shopping and preparation for family needs

    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
    \views
    -0.08
    oru
    -0.07
    iez
    -0.07
    wich
    -0.07
    WithOptions
    -0.07
    ozem
    -0.07
    é§ħå¾ĴæŃ©
    -0.07
    ypy
    -0.06
    _release
    -0.06
    neau
    -0.06
    POSITIVE LOGITS
     sizes
    0.07
     wear
    0.07
     size
    0.06
    æij©
    0.06
    ilo
    0.06
     worn
    0.06
     Sizes
    0.06
    (size
    0.06
    _dma
    0.06
     sizing
    0.06
    Activations Density 0.007%

    No Known Activations