© 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. 121264
    Prev
    Next
    INDEX
    Explanations

    descriptors of political corruption and dysfunction

    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
    üçük
    -0.07
    ág
    -0.07
    ¼
    -0.06
    кав
    -0.06
     strugg
    -0.06
    immel
    -0.06
    Åij
    -0.06
    liga
    -0.06
    ìķ½
    -0.06
    Segue
    -0.06
    POSITIVE LOGITS
     leaks
    0.07
    elier
    0.06
    ongan
    0.06
    chs
    0.06
    æķı
    0.06
     leak
    0.06
    omin
    0.06
    memo
    0.06
    amespace
    0.06
    hs
    0.06
    Activations Density 0.001%

    No Known Activations