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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 5-LLAMASCOPE-RES-131K
    11. 125870
    Prev
    Next
    INDEX
    Explanations

    phrases related to notifications and alerts

    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
    ÑıÑģ
    -0.07
    ajs
    -0.07
    ằ
    -0.07
    avou
    -0.06
     Spoon
    -0.06
    asz
    -0.06
     пÑĢиклад
    -0.06
    rani
    -0.06
    enza
    -0.06
    asar
    -0.06
    POSITIVE LOGITS
     Dexter
    0.07
    _avail
    0.06
    hol
    0.06
    .syntax
    0.06
    progressbar
    0.06
    ilk
    0.06
    éŃļ
    0.06
    é±¼
    0.06
    رÙĪت
    0.06
    ãĥIJãĥ¼
    0.06
    Activations Density 0.006%

    No Known Activations