© 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. 18492
    Prev
    Next
    INDEX
    Explanations

    references to religious concepts, particularly those related to God and His son

    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
    gid
    -0.07
    ymi
    -0.07
     Yoshi
    -0.07
    unks
    -0.07
    zek
    -0.07
    azzi
    -0.06
    abus
    -0.06
    ülü
    -0.06
     Bur
    -0.06
    gi
    -0.06
    POSITIVE LOGITS
    prav
    0.06
     Baz
    0.06
     hyp
    0.06
    swick
    0.06
    çĭ
    0.06
    .SpringBootApplication
    0.06
    Enumerator
    0.06
     cez
    0.06
     Creed
    0.06
    кон
    0.06
    Activations Density 0.002%

    No Known Activations