© 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. 56940
    Prev
    Next
    INDEX
    Explanations

    terms related to pronunciation and phonetics

    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
    itage
    -0.07
    meld
    -0.07
    HeaderCode
    -0.07
    ä¾Ľ
    -0.06
    rary
    -0.06
    strar
    -0.06
    .sm
    -0.06
    quirer
    -0.06
    uring
    -0.06
    olie
    -0.06
    POSITIVE LOGITS
    pron
    0.19
     pronounced
    0.18
     pronounce
    0.15
     pron
    0.15
     Pron
    0.14
     pronunciation
    0.12
    spell
    0.09
     spelling
    0.08
     spelled
    0.08
     spell
    0.08
    Activations Density 0.032%

    No Known Activations