© 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. 14231
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental threats and natural disasters

    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
    umpt
    -0.08
    İ·
    -0.07
    éĥ
    -0.07
    âĶĺ
    -0.07
    aurant
    -0.07
    utzer
    -0.07
    Äı
    -0.07
    postal
    -0.06
    imony
    -0.06
    _ACTIVE
    -0.06
    POSITIVE LOGITS
     ts
    0.08
     wave
    0.08
     waves
    0.07
    unami
    0.07
     tsunami
    0.07
     earthquake
    0.07
     Pacific
    0.06
     warning
    0.06
     shallow
    0.06
     outr
    0.06
    Activations Density 0.004%

    No Known Activations