© 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. 17-LLAMASCOPE-RES-131K
    11. 126101
    Prev
    Next
    INDEX
    Explanations

    references to human rights events and discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    insk
    -0.07
    лки
    -0.07
    -<?
    -0.06
    insky
    -0.06
    ovit
    -0.06
     <!
    -0.06
    ová
    -0.06
    «ĺ
    -0.06
     tiết
    -0.06
     :č↵
    -0.06
    POSITIVE LOGITS
     https
    0.13
     @
    0.11
     #
    0.10
     http
    0.09
    https
    0.08
     &
    0.08
     (@
    0.07
     today
    0.07
     &,
    0.07
    agram
    0.07
    Activations Density 0.028%

    No Known Activations