© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 69501
    Prev
    Next
    INDEX
    Explanations

    terms related to pronunciation and spelling differences

    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
    mos
    -0.08
    arp
    -0.07
    ugin
    -0.06
    æĻ
    -0.06
    icolor
    -0.06
    erde
    -0.06
    une
    -0.06
    -Language
    -0.06
    quine
    -0.06
    mscorlib
    -0.05
    POSITIVE LOGITS
     pronunciation
    0.09
    æŃ£ç¡®
    0.08
     correct
    0.08
     correctly
    0.08
    otron
    0.08
     Proper
    0.08
    correct
    0.07
     pronounce
    0.07
    proper
    0.07
    ARIANT
    0.07
    Activations Density 0.008%

    No Known Activations