© 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. 14103
    Prev
    Next
    INDEX
    Explanations

    themes related to personal struggle and societal pressures

    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
    ichni
    -0.08
    anan
    -0.07
    _BC
    -0.07
    æ¾
    -0.07
     mát
    -0.07
    dds
    -0.07
    arges
    -0.07
    /gin
    -0.07
    isky
    -0.07
     Leban
    -0.07
    POSITIVE LOGITS
     women
    0.06
     succ
    0.06
     scrim
    0.06
     narrator
    0.05
     exc
    0.05
    0.05
    ï¿
    0.05
     mostly
    0.05
     minute
    0.05
     doi
    0.05
    Activations Density 0.003%

    No Known Activations