© 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. 89704
    Prev
    Next
    INDEX
    Explanations

    phrases related to mining and its associated dangers

    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
    ulumi
    -0.08
    APON
    -0.08
    ycin
    -0.07
    ouden
    -0.07
    kün
    -0.07
    åĿ¦
    -0.06
    gota
    -0.06
    licative
    -0.06
    estre
    -0.06
    /theme
    -0.06
    POSITIVE LOGITS
     underground
    0.10
     miners
    0.09
     worker
    0.08
     Underground
    0.08
     work
    0.08
     workers
    0.08
     shaft
    0.08
     union
    0.08
     safety
    0.08
     miner
    0.08
    Activations Density 0.025%

    No Known Activations