© 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. 17912
    Prev
    Next
    INDEX
    Explanations

    phrases related to government initiatives and policies

    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
    彦
    -0.07
    ivery
    -0.07
    wal
    -0.07
    jac
    -0.07
     COPYRIGHT
    -0.06
    è¡
    -0.06
    ãĥĨãĥ«
    -0.06
    istrovstvÃŃ
    -0.06
    ipp
    -0.06
    @dynamic
    -0.06
    POSITIVE LOGITS
     plan
    0.08
     Plan
    0.07
    clamp
    0.07
     program
    0.07
     strategy
    0.07
     Act
    0.06
     Project
    0.06
     project
    0.06
    ajs
    0.06
     Bill
    0.06
    Activations Density 0.064%

    No Known Activations