© 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. 31692
    Prev
    Next
    INDEX
    Explanations

    phrases related to changes and transformations

    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
    /ay
    -0.07
    lez
    -0.06
     kans
    -0.06
    uchen
    -0.06
    gle
    -0.06
    ulp
    -0.06
    retch
    -0.06
    ÐIJÐł
    -0.06
    ajan
    -0.06
    anzi
    -0.06
    POSITIVE LOGITS
     focus
    0.07
     direction
    0.07
    å±Ĭ
    0.07
     Parad
    0.07
     tack
    0.07
    uxtap
    0.06
    ystate
    0.06
     zda
    0.06
    /reset
    0.06
    ichtet
    0.06
    Activations Density 0.008%

    No Known Activations