© 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. 123422
    Prev
    Next
    INDEX
    Explanations

    elements related to language and translation

    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
     thÆ°Æ¡ng
    -0.08
    ovat
    -0.07
    enburg
    -0.07
    rib
    -0.07
    redient
    -0.06
    hon
    -0.06
    loor
    -0.06
    iddy
    -0.06
    ubits
    -0.06
    uppercase
    -0.06
    POSITIVE LOGITS
     IPA
    0.08
    igli
    0.07
     USAGE
    0.07
     Farrell
    0.06
     opak
    0.06
     Parad
    0.06
     Imper
    0.06
    ço
    0.06
    asm
    0.06
     Antar
    0.06
    Activations Density 0.004%

    No Known Activations