© 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. 9-LLAMASCOPE-RES-131K
    11. 94080
    Prev
    Next
    INDEX
    Explanations

    text related to military service or enforcement

    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
    vore
    -0.07
    amac
    -0.06
    boro
    -0.06
     defaultManager
    -0.06
    steller
    -0.06
     Orientation
    -0.06
    loser
    -0.06
    ÑĤÑĥÑĢа
    -0.06
     Flexible
    -0.06
    Unsafe
    -0.06
    POSITIVE LOGITS
    .SDK
    0.07
     Baker
    0.06
    ìĸ´
    0.06
    .ide
    0.06
    ç¥Ŀ
    0.06
     yên
    0.06
     Brewer
    0.06
    ë°±
    0.06
    обов
    0.06
    .wikipedia
    0.06
    Activations Density 0.000%

    No Known Activations