© 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. 325
    Prev
    Next
    INDEX
    Explanations

    electoral and political event outcomes

    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
    onomy
    -0.08
    ìĨIJ
    -0.07
    embro
    -0.06
    cono
    -0.06
    olah
    -0.06
    SCRI
    -0.06
     Whe
    -0.06
     whe
    -0.06
    irá
    -0.06
     cref
    -0.06
    POSITIVE LOGITS
    Platforms
    0.07
     Platforms
    0.07
     Hoe
    0.06
    antaged
    0.06
    hari
    0.06
    ican
    0.06
     Hakk
    0.06
    icy
    0.06
     पद
    0.06
     platforms
    0.06
    Activations Density 0.015%

    No Known Activations