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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 61451
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations

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

    Mathematical equality or relation symbols ("=", "≥", etc.) that connect expressions in LaTeX mathematical notation, typically within equation environments.

    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
    assi
    -0.07
    DEX
    -0.07
    roe
    -0.07
    assin
    -0.07
     Mar
    -0.07
    orate
    -0.06
    prompt
    -0.06
    rete
    -0.06
    akra
    -0.06
    ateurs
    -0.06
    POSITIVE LOGITS
     ç·¨
    0.07
    ARGET
    0.07
    indr
    0.06
    endo
    0.06
    ãĥ³ãĤ°
    0.06
    _firestore
    0.06
    opis
    0.06
    ird
    0.06
    \Php
    0.06
    inge
    0.06
    Activations Density 0.279%

    No Known Activations