Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 44098
    Prev
    Next
    INDEX
    Explanations

    instances of the letter "d" and its various forms in words

    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
     Spl
    -0.07
     spl
    -0.06
    ntax
    -0.06
    Spl
    -0.06
    -<?
    -0.06
    962
    -0.06
     dust
    -0.06
    adero
    -0.06
    odem
    -0.06
    acyj
    -0.06
    POSITIVE LOGITS
    rows
    0.24
    izziness
    0.21
    ROWS
    0.15
    izz
    0.14
    row
    0.14
     rows
    0.14
    izzy
    0.13
    azed
    0.13
    rowse
    0.12
    Rows
    0.12
    Activations Density 0.005%

    No Known Activations