© 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. 17-LLAMASCOPE-RES-131K
    11. 3933
    Prev
    Next
    INDEX
    Explanations

    content related to programming, websites, and technical documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    End-of-section markers in digital content, particularly hyperlinks, closing punctuation, and formatting elements that indicate the conclusion of a paragraph or content section before a new section begins.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    Ð
    -0.06
     READ
    -0.06
     ↵↵
    -0.06
     Read
    -0.06
     [](
    -0.06
     Kidd
    -0.06
    ãģĹãģĭ
    -0.06
    oot
    -0.06
    oph
    -0.06
    znik
    -0.06
    POSITIVE LOGITS
    /WebAPI
    0.08
    âĨIJ
    0.08
    itemap
    0.07
    ãĢĤ↵↵↵↵↵↵
    0.07
    @student
    0.07
    olan
    0.07
    engin
    0.07
    multipart
    0.06
    :UIAlert
    0.06
    //{{
    0.06
    Activations Density 2.767%

    No Known Activations