© 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. 1158
    Prev
    Next
    INDEX
    Explanations

    phrases indicating comparisons or relationships between different entities or groups

    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
    lech
    -0.09
     nowhere
    -0.08
    ormsg
    -0.07
     ULONG
    -0.07
    gra
    -0.07
    iset
    -0.07
    isé
    -0.07
    leh
    -0.07
    ÑĦи
    -0.06
    uum
    -0.06
    POSITIVE LOGITS
     åĪ°
    0.07
    åĪ°
    0.06
    -to
    0.06
     nÃły
    0.06
     unto
    0.06
    ãģĵãģ¨ãģ«
    0.06
    antal
    0.06
    ë§Īëĭ¤
    0.05
    ics
    0.05
    елÑİ
    0.05
    Activations Density 0.014%

    No Known Activations