© 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. 77951
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating inclusion or addition

    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
    incare
    -0.07
    oppins
    -0.07
    enic
    -0.07
    oure
    -0.07
    enal
    -0.06
    oningen
    -0.06
    rescia
    -0.06
    orra
    -0.06
    ureau
    -0.06
     Kab
    -0.06
    POSITIVE LOGITS
    .blank
    0.07
    IEW
    0.07
    ars
    0.07
     ÙħجÙħÙĪØ¹
    0.06
     Berk
    0.06
    ocracy
    0.06
     Pes
    0.06
    ZY
    0.06
    tek
    0.06
    ((__
    0.06
    Activations Density 0.000%

    No Known Activations