© 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. 58173
    Prev
    Next
    INDEX
    Explanations

    the presence of verbs in various tenses, particularly focusing on the word "had."

    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
    sole
    -0.07
     Tray
    -0.07
    awah
    -0.06
    Å¡k
    -0.06
    oline
    -0.06
    lein
    -0.06
    otto
    -0.06
     Klein
    -0.06
    ider
    -0.06
    ove
    -0.06
    POSITIVE LOGITS
     earlier
    0.11
     Earlier
    0.09
     previously
    0.09
     already
    0.09
    Earlier
    0.07
     سابÙĤ
    0.07
     déjÃł
    0.07
    CHASE
    0.07
     recently
    0.07
     ведÑĮ
    0.07
    Activations Density 0.045%

    No Known Activations