© 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. 15648
    Prev
    Next
    INDEX
    Explanations

    phrases that express anticipation or interest

    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
    law
    -0.07
    ptal
    -0.07
    coles
    -0.07
    ضا
    -0.06
    agu
    -0.06
    agara
    -0.06
    ifar
    -0.06
    olland
    -0.06
    ick
    -0.06
    .bc
    -0.06
    POSITIVE LOGITS
    (ed
    0.07
    æľŁå¾ħ
    0.07
    plex
    0.07
    ÂŃing
    0.07
    çļĦæĺ¯
    0.06
     hope
    0.06
    Ing
    0.06
    å¸ĮæľĽ
    0.06
     saja
    0.06
    ãĥ¼ãĥĦ
    0.06
    Activations Density 0.006%

    No Known Activations