© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 53997
    Prev
    Next
    INDEX
    Explanations

    instances of the word "tell" and its variations in different contexts

    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
    Dos
    -0.07
    ÑĪки
    -0.06
     Dos
    -0.06
    CO
    -0.06
    ha
    -0.06
    elf
    -0.05
    oren
    -0.05
     sh
    -0.05
    co
    -0.05
     fat
    -0.05
    POSITIVE LOGITS
    ãĥ¼ãĥł
    0.07
    äºŃ
    0.07
    ingly
    0.07
    uae
    0.07
     جÙħعÛĮت
    0.07
    ikit
    0.07
    stile
    0.07
    zem
    0.07
    -Ta
    0.07
    pNet
    0.07
    Activations Density 0.003%

    No Known Activations