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

    Neuronpedia

    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. 40058
    Prev
    Next
    INDEX
    Explanations

    political commentary and critique, particularly regarding election candidates and their viability

    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
    neas
    -0.06
    affer
    -0.06
     WARRANT
    -0.06
    uro
    -0.06
    ÏĥÏĦά
    -0.06
    eren
    -0.06
    æĺĮ
    -0.06
    usan
    -0.06
    .pretty
    -0.06
    usic
    -0.06
    POSITIVE LOGITS
     unity
    0.07
     margins
    0.07
     win
    0.07
    unity
    0.07
    Gro
    0.06
     unins
    0.06
    okens
    0.06
     Team
    0.06
     margin
    0.06
    Messaging
    0.06
    Activations Density 0.026%

    No Known Activations