© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 5474
    Prev
    Next
    INDEX
    Explanations

    references to political mandates and governmental processes

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    fik
    -0.07
    udu
    -0.07
    微软éĽħé»ij
    -0.07
    iese
    -0.06
    оÑıÑĤ
    -0.06
    é¾Ħ
    -0.06
    éĽ²
    -0.06
    олаг
    -0.06
    ETY
    -0.06
    roit
    -0.06
    POSITIVE LOGITS
     mandate
    0.12
    mand
    0.11
     popular
    0.10
     mandates
    0.09
    Popular
    0.09
     Popular
    0.08
     Mand
    0.08
     majority
    0.08
    popular
    0.08
     popularity
    0.08
    Activations Density 0.088%

    No Known Activations