© 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. 124489
    Prev
    Next
    INDEX
    Explanations

    references to government officials and calls to action for political accountability

    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
    iek
    -0.07
    leared
    -0.06
    ils
    -0.06
    rab
    -0.06
    à¹Ģสร
    -0.05
     Clock
    -0.05
    οι
    -0.05
     Anxiety
    -0.05
    åł±
    -0.05
     Presentation
    -0.05
    POSITIVE LOGITS
    -alist
    0.08
    undles
    0.07
     petitions
    0.07
    èįĴ
    0.07
    .scalablytyped
    0.07
    ãĥĮ
    0.07
    /lic
    0.07
    оÑģÑĤÑĥп
    0.07
     awareness
    0.07
    uentes
    0.06
    Activations Density 0.033%

    No Known Activations