© 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. 69923
    Prev
    Next
    INDEX
    Explanations

    phrases related to legislation and public policy concerns

    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
    612
    -0.06
     Hlav
    -0.06
    613
    -0.06
    683
    -0.06
    ķĮ
    -0.06
    FC
    -0.06
    orman
    -0.06
    adal
    -0.06
     Urs
    -0.06
     FC
    -0.06
    POSITIVE LOGITS
    oldem
    0.08
     eius
    0.07
    .RightToLeft
    0.07
    GINE
    0.07
    ller
    0.07
    increment
    0.07
    ypse
    0.07
    碼
    0.07
    ocale
    0.07
    Increment
    0.07
    Activations Density 0.028%

    No Known Activations