© 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. 121644
    Prev
    Next
    INDEX
    Explanations

    emotional and moral themes related to motherhood and compassion

    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
    142
    -0.08
    140
    -0.06
    agi
    -0.06
    atty
    -0.06
    emin
    -0.06
    350
    -0.06
     recently
    -0.06
    aland
    -0.06
     NavParams
    -0.06
    125
    -0.06
    POSITIVE LOGITS
     alike
    0.08
    ãĥ¥
    0.07
    [:]
    0.06
    otros
    0.06
    ylvania
    0.06
    ÙĪت
    0.06
     пл
    0.06
    éĨ
    0.06
    ALLED
    0.06
    olik
    0.06
    Activations Density 0.001%

    No Known Activations