© 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. 116347
    Prev
    Next
    INDEX
    Explanations

    references to crystalline structures and properties

    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
    estro
    -0.06
    iesz
    -0.06
    ะ
    -0.06
    ryn
    -0.06
    浦
    -0.06
    addy
    -0.06
    iw
    -0.06
    PÅĻi
    -0.06
     Ellis
    -0.06
    lessly
    -0.06
    POSITIVE LOGITS
    -clear
    0.09
     crystal
    0.09
     Crystal
    0.08
    log
    0.08
    loid
    0.08
    ize
    0.08
    æĻ¶
    0.08
    çµIJ
    0.08
    Crystal
    0.08
     cryst
    0.07
    Activations Density 0.015%

    No Known Activations