© 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. 105894
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting elements in the text

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

    Navigation elements or section headers that separate distinct content blocks on websites, often appearing between paragraphs.

    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
    ãĥ¼ãĤº
    -0.08
    _Construct
    -0.07
    {{{
    -0.07
    304
    -0.07
    ards
    -0.07
    295
    -0.07
    orthand
    -0.07
    ãģİ
    -0.07
     Zot
    -0.06
    ALLY
    -0.06
    POSITIVE LOGITS
     Shall
    0.07
    emm
    0.06
    igli
    0.06
    ckeditor
    0.06
    odia
    0.06
    Ĭ
    0.06
     shall
    0.06
    rå
    0.06
     Antar
    0.06
     UNIVERS
    0.06
    Activations Density 0.089%

    No Known Activations