© 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. 80761
    Prev
    Next
    INDEX
    Explanations

    specific words related to government or military contexts

    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
    rift
    -0.07
    ardon
    -0.07
    enta
    -0.06
    ycop
    -0.06
    itic
    -0.06
    ptr
    -0.06
    ADED
    -0.06
    ноÑĪ
    -0.06
    entic
    -0.06
    rus
    -0.06
    POSITIVE LOGITS
    edm
    0.07
    iro
    0.07
     iov
    0.06
    643
    0.06
    év
    0.06
     Cros
    0.06
    hue
    0.06
    (*)(
    0.06
    WidgetItem
    0.06
    etwork
    0.06
    Activations Density 0.020%

    No Known Activations