© 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. 18564
    Prev
    Next
    INDEX
    Explanations

    expressions of emotions and sentiments, particularly feelings of support, disappointment, and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ัà¸Ī
    -0.07
    ken
    -0.06
    aldo
    -0.06
    park
    -0.06
     Ambient
    -0.06
    fé
    -0.06
    neau
    -0.06
    aldi
    -0.06
    632
    -0.06
     qui
    -0.06
    POSITIVE LOGITS
    602
    0.09
    quete
    0.08
    HeaderCode
    0.08
    unning
    0.07
     thÆ°
    0.07
    anges
    0.07
    aper
    0.07
    çĦ
    0.06
    oyal
    0.06
    æ´ŀ
    0.06
    Activations Density 0.018%

    No Known Activations