© 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. 38526
    Prev
    Next
    INDEX
    Explanations

    the repeated use of the word "been."

    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
    éĥİ
    -0.08
    yz
    -0.07
     VÅ¡ech
    -0.07
    still
    -0.07
    éĢīæĭ
    -0.07
    uhan
    -0.07
    cg
    -0.07
    oho
    -0.07
     soon
    -0.07
    soon
    -0.07
    POSITIVE LOGITS
     lately
    0.14
     since
    0.13
     recently
    0.12
    _since
    0.10
    /is
    0.10
    since
    0.10
    Recently
    0.09
     Recently
    0.09
    Since
    0.08
    以æĿ¥
    0.08
    Activations Density 0.097%

    No Known Activations