© 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. 91637
    Prev
    Next
    INDEX
    Explanations

    interactions and communication between individuals, particularly through messages and feedback

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ocs
    -0.07
    éľ²
    -0.06
    izard
    -0.06
    .)↵↵↵↵
    -0.06
     Thom
    -0.06
    æ³
    -0.06
    omial
    -0.06
    ¹æŀľ
    -0.06
    usp
    -0.06
    ãĥ¼ãĥĹ
    -0.06
    POSITIVE LOGITS
    inel
    0.08
     signals
    0.08
    message
    0.07
    asc
    0.07
    åĩºåİ»
    0.07
    missive
    0.07
     message
    0.06
     Ø¥ÙĦÙĬÙĩ
    0.06
    signals
    0.06
    Signals
    0.06
    Activations Density 0.054%

    No Known Activations