© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 2181
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "this" and its variations

    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
    ilib
    -0.07
     èµ
    -0.07
    .tail
    -0.07
    à¥Īà¤ł
    -0.07
    à¸Ńà¸ĩ
    -0.07
     Ñĩим
    -0.07
    zdy
    -0.07
    سÙĪÙĨ
    -0.07
    خاÙĨÙĩ
    -0.07
    iyon
    -0.06
    POSITIVE LOGITS
    irie
    0.07
    į¼
    0.06
    yas
    0.06
     is
    0.06
    aska
    0.06
     therefore
    0.06
    acic
    0.06
     aside
    0.06
     this
    0.06
     however
    0.06
    Activations Density 0.033%

    No Known Activations