© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 127045
    Prev
    Next
    INDEX
    Explanations

    references to political issues and social commentary

    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
    alama
    -0.08
    allo
    -0.07
     cupid
    -0.07
    meli
    -0.07
    inker
    -0.07
    ÐŁÐŀ
    -0.07
    reserved
    -0.07
    .gdx
    -0.07
    yen
    -0.07
    rlen
    -0.07
    POSITIVE LOGITS
     ÂŃ
    0.07
    âĢIJ
    0.07
     .↵↵
    0.07
     .↵
    0.06
     
    0.06
     Mn
    0.06
     U
    0.06
     termin
    0.06
    âĢħ
    0.06
     racial
    0.06
    Activations Density 0.003%

    No Known Activations