© 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. 60721
    Prev
    Next
    INDEX
    Explanations

    elements related to website structure and layout

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

    HTML/CSS/programming elements that denote layout components, structural elements, or programming identifiers in website code or application development files.

    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
    erland
    -0.06
    opensource
    -0.06
    -envelope
    -0.06
    oly
    -0.06
     Blanc
    -0.06
     ir
    -0.06
     pseud
    -0.06
    âr
    -0.05
    Overview
    -0.05
    327
    -0.05
    POSITIVE LOGITS
    pdev
    0.07
    etur
    0.07
    vero
    0.07
    tru
    0.07
    tran
    0.07
    ãĢijãĢIJ
    0.06
     left
    0.06
    :left
    0.06
     content
    0.06
    ÑĢава
    0.06
    Activations Density 0.027%

    No Known Activations