© 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. 104027
    Prev
    Next
    INDEX
    Explanations

    terms related to financial structures and models

    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
    enci
    -0.07
    aid
    -0.07
    ãģŁãĤī
    -0.07
    Uses
    -0.06
     @}
    -0.06
     behalf
    -0.06
    quete
    -0.06
     respectively
    -0.06
    iked
    -0.05
    emme
    -0.05
    POSITIVE LOGITS
    alone
    0.09
     seemed
    0.09
     seems
    0.08
     is
    0.08
     merupakan
    0.08
    æĺ¯æĪij
    0.08
    æĺ¯ä¸į
    0.07
     adalah
    0.07
     bietet
    0.07
     alone
    0.07
    Activations Density 0.064%

    No Known Activations