© 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. 15-LLAMASCOPE-RES-131K
    11. 104263
    Prev
    Next
    INDEX
    Explanations

    expressions of statistical support or opposition to political issues

    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
    orners
    -0.08
    uve
    -0.07
    akter
    -0.07
    baru
    -0.07
    alfa
    -0.07
    oz
    -0.07
    /Dk
    -0.07
    oka
    -0.07
    omanip
    -0.07
    serter
    -0.07
    POSITIVE LOGITS
     Rubin
    0.06
    ismus
    0.06
     Dyn
    0.06
     secondary
    0.06
     tap
    0.06
     national
    0.05
    egin
    0.05
    731
    0.05
    usch
    0.05
    717
    0.05
    Activations Density 0.002%

    No Known Activations