© 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. 83836
    Prev
    Next
    INDEX
    Explanations

    elements related to programming logic and functions

    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
    flix
    -0.07
    iveau
    -0.07
    isku
    -0.07
    awk
    -0.07
    ogg
    -0.06
    inar
    -0.06
    aval
    -0.06
    ambre
    -0.06
    avax
    -0.06
    edia
    -0.06
    POSITIVE LOGITS
     ëij
    0.07
    .populate
    0.06
    ë¥
    0.06
    pus
    0.06
    atos
    0.06
     intim
    0.06
    çģ
    0.06
    é¼ĵ
    0.06
    ollo
    0.06
    iterated
    0.06
    Activations Density 0.005%

    No Known Activations