© 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. 28455
    Prev
    Next
    INDEX
    Explanations

    references to housing and infrastructure improvements

    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
     Earn
    -0.08
    DidChange
    -0.07
    PÅĻi
    -0.07
    ẻ
    -0.07
    erer
    -0.07
    (æľĪ
    -0.07
    à¥ī
    -0.07
    Earn
    -0.07
    .Syntax
    -0.07
    linger
    -0.07
    POSITIVE LOGITS
     additional
    0.09
     extra
    0.08
     Extra
    0.08
     Additional
    0.08
     addition
    0.07
     new
    0.07
    jam
    0.07
     Hiring
    0.07
     tw
    0.06
     promised
    0.06
    Activations Density 0.018%

    No Known Activations