© 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. 108943
    Prev
    Next
    INDEX
    Explanations

    references to religious laws and teachings in an Islamic context

    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
    Ỽ
    -0.07
    attern
    -0.06
    ÃŃrk
    -0.06
     Template
    -0.06
    aleb
    -0.06
    isko
    -0.06
    erson
    -0.06
    áºŃu
    -0.06
    ernal
    -0.05
    itou
    -0.05
    POSITIVE LOGITS
    кеÑĤ
    0.08
     شع
    0.07
    ì½ĺ
    0.07
    CRET
    0.07
     skill
    0.07
    -learning
    0.07
    098
    0.07
     trai
    0.07
     ability
    0.07
    iven
    0.07
    Activations Density 0.013%

    No Known Activations