© 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. 80234
    Prev
    Next
    INDEX
    Explanations

    concepts related to social and political structures

    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
    pute
    -0.06
    ady
    -0.06
     oma
    -0.06
    pei
    -0.06
     philosoph
    -0.06
    peg
    -0.06
    ORM
    -0.06
     chatt
    -0.06
    vere
    -0.06
     suddenly
    -0.06
    POSITIVE LOGITS
     actors
    0.07
     outcomes
    0.07
    åĬĽéĩı
    0.07
     Bale
    0.06
     actor
    0.06
    ucht
    0.06
    emonic
    0.06
    éŁ
    0.06
     outcome
    0.06
     fp
    0.06
    Activations Density 0.008%

    No Known Activations