© 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. 83342
    Prev
    Next
    INDEX
    Explanations

    names or surnames with the letter combination "ett."

    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
    ycin
    -0.08
    ietet
    -0.08
    iego
    -0.08
    stag
    -0.07
    neys
    -0.07
    ictory
    -0.07
    /Area
    -0.07
    .LENGTH
    -0.07
    astr
    -0.07
    aires
    -0.07
    POSITIVE LOGITS
    ters
    0.09
    zel
    0.07
     Knight
    0.06
    chem
    0.06
     forth
    0.06
     Millennium
    0.06
    osterone
    0.06
    hel
    0.06
    lesen
    0.06
     advert
    0.06
    Activations Density 0.024%

    No Known Activations