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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 14527
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to web programming or markup structure

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

    Special characters and delimiters in HTML/code contexts, particularly those defining structure, string boundaries, or empty element states.

    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
    izar
    -0.06
    re
    -0.06
    opus
    -0.06
    หà¸Ļ
    -0.06
    nl
    -0.06
    Îĸ
    -0.06
    ze
    -0.06
     myself
    -0.06
    overs
    -0.06
    2
    -0.06
    POSITIVE LOGITS
     Loading
    0.12
     loading
    0.11
    loading
    0.11
    Loading
    0.10
     empty
    0.10
    .loading
    0.10
    -empty
    0.10
    -loading
    0.10
    empty
    0.09
     Empty
    0.09
    Activations Density 0.039%

    No Known Activations