© 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. 53714
    Prev
    Next
    INDEX
    Explanations

    references to significant cultural or spiritual elements

    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
    327
    -0.07
    515
    -0.07
     Shield
    -0.07
     turb
    -0.06
     prow
    -0.06
    415
    -0.06
    636
    -0.06
    irie
    -0.06
    æĬķ
    -0.06
    637
    -0.06
    POSITIVE LOGITS
    parity
    0.06
     VÆ°á»Ŀn
    0.06
    ovu
    0.06
    çݲ
    0.06
    ripe
    0.06
    ndef
    0.06
    leaflet
    0.06
    idir
    0.06
    Disappear
    0.06
    juan
    0.06
    Activations Density 0.001%

    No Known Activations