© 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. 62943
    Prev
    Next
    INDEX
    Explanations

    instances of the word "been" and its variations, indicating a focus on past experiences and occurrences

    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
     hereby
    -0.08
    /question
    -0.07
    ÃĹ↵↵
    -0.07
     now
    -0.07
    <KeyValuePair
    -0.07
    chia
    -0.07
    ì²Ļ
    -0.06
    enheim
    -0.06
    otre
    -0.06
    abin
    -0.06
    POSITIVE LOGITS
     earlier
    0.17
     Earlier
    0.13
    Earlier
    0.12
     previously
    0.12
     originally
    0.11
     previous
    0.11
     hadn
    0.11
    had
    0.10
     habÃŃa
    0.09
     Previously
    0.09
    Activations Density 0.117%

    No Known Activations