© 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 EvalsExportsAPI 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. 77288
    Prev
    Next
    INDEX
    Explanations

    themes related to political dynamics and electoral reform

    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
    opic
    -0.07
    ost
    -0.06
    ocoa
    -0.06
    ÅŁÄ±
    -0.06
    ģn
    -0.06
    .Sn
    -0.06
     Maul
    -0.06
     Magnum
    -0.06
    anes
    -0.06
    оÑģÑĤ
    -0.06
    POSITIVE LOGITS
     Corruption
    0.08
     Transparency
    0.08
     corruption
    0.08
     grid
    0.07
     Gerr
    0.07
     transparency
    0.07
     citizen
    0.07
     cand
    0.06
    raith
    0.06
     corrupted
    0.06
    Activations Density 0.031%

    No Known Activations