© 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. 70847
    Prev
    Next
    INDEX
    Explanations

    references to mainstream and pioneering ideas or concepts

    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
    شت
    -0.07
    ÑĢаÑħов
    -0.07
    adnÃŃ
    -0.06
    /locale
    -0.06
    ิà¸į
    -0.06
    IMS
    -0.06
    ockey
    -0.06
     BÃłi
    -0.06
    inheritDoc
    -0.06
     Strange
    -0.06
    POSITIVE LOGITS
     maybe
    0.07
    Nr
    0.06
    .nr
    0.06
    ãĥĹãĥª
    0.06
     Maybe
    0.06
     visibly
    0.06
    axy
    0.06
     incentiv
    0.06
    deck
    0.06
    Maybe
    0.06
    Activations Density 0.000%

    No Known Activations