© 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. 42690
    Prev
    Next
    INDEX
    Explanations

    expressions of empathy and support in conversations

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

    Username identifiers and their associated comments in online forum/discussion board posts, often appearing in a structured format within threaded conversations.

    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
    ást
    -0.08
     Leban
    -0.08
    aldi
    -0.08
     ActionType
    -0.07
    zion
    -0.07
    pedia
    -0.07
    ãĥ¥
    -0.06
     jadx
    -0.06
    atten
    -0.06
     Incredible
    -0.06
    POSITIVE LOGITS
     answer
    0.08
    ħ
    0.07
    åĽŀçŃĶ
    0.07
    iele
    0.07
     answered
    0.07
     Answer
    0.07
     Depends
    0.07
    æĪij
    0.06
    answer
    0.06
    _answer
    0.06
    Activations Density 0.011%

    No Known Activations