© 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. 120421
    Prev
    Next
    INDEX
    Explanations

    references to political issues and governance

    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
    contre
    -0.08
    .appspot
    -0.08
    oyer
    -0.07
    ALES
    -0.07
    olio
    -0.07
    âĻ¡
    -0.07
    LOPT
    -0.07
    Disposed
    -0.07
    atha
    -0.07
    uib
    -0.07
    POSITIVE LOGITS
     incredible
    0.06
     prem
    0.06
     pro
    0.06
     Ambassador
    0.05
     Administrator
    0.05
     world
    0.05
     counseling
    0.05
     absent
    0.05
    503
    0.05
     instruct
    0.05
    Activations Density 0.001%

    No Known Activations