© 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. 103855
    Prev
    Next
    INDEX
    Explanations

    instances of significant or impactful events

    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
    warts
    -0.08
    ephir
    -0.07
    oder
    -0.07
    icates
    -0.07
    noch
    -0.07
    assed
    -0.07
    udem
    -0.07
    inqu
    -0.07
    cret
    -0.07
    ardown
    -0.07
    POSITIVE LOGITS
     ever
    0.06
     once
    0.06
    adays
    0.06
     today
    0.06
     eines
    0.06
    Certain
    0.05
     nearly
    0.05
     certain
    0.05
    one
    0.05
    ARRIER
    0.05
    Activations Density 0.093%

    No Known Activations