© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 18654
    Prev
    Next
    INDEX
    Explanations

    terms related to management and community engagement

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Tag words and category labels that appear at the bottom of online articles or blog posts, often representing topics, keywords, or navigation elements for content categorization.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219
    Triggered 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
    Negative Logits
    .scalablytyped
    -0.07
     Verd
    -0.07
    @",
    -0.06
     ấy
    -0.06
    çĶ³
    -0.06
     meÅŁ
    -0.06
    Ïĥα
    -0.06
    #ad
    -0.06
    ëĮĢë¡ľ
    -0.06
    _BT
    -0.06
    POSITIVE LOGITS
    akit
    0.08
     Uncategorized
    0.08
    575
    0.07
    TERN
    0.07
    eteor
    0.07
    576
    0.07
    tsky
    0.06
    RIX
    0.06
    erequisites
    0.06
    obby
    0.06
    Activations Density 0.006%

    No Known Activations