© 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. 79282
    Prev
    Next
    INDEX
    Explanations

    references to specific political events and decisions

    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
    utenberg
    -0.07
    osen
    -0.06
    ijkstra
    -0.06
     Wich
    -0.06
    ëŁ½
    -0.06
    595
    -0.06
     Brick
    -0.06
     Butter
    -0.06
     Beet
    -0.06
    BarButton
    -0.06
    POSITIVE LOGITS
     legacy
    0.08
     hel
    0.08
     under
    0.08
     inherit
    0.08
     Obama
    0.08
     outgoing
    0.07
     inherited
    0.07
     predecessor
    0.07
     inher
    0.07
     President
    0.07
    Activations Density 0.061%

    No Known Activations