© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 62299
    Prev
    Next
    INDEX
    Explanations

    references to legislation aimed at protecting children and veterans

    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
    aign
    -0.08
    wahl
    -0.07
     political
    -0.07
    anan
    -0.07
     politicians
    -0.07
     Political
    -0.07
     politician
    -0.06
    anova
    -0.06
    õ
    -0.06
    æĶ¿æ²»
    -0.06
    POSITIVE LOGITS
    udy
    0.08
    urum
    0.07
     PREFIX
    0.06
     recon
    0.06
     caret
    0.06
    antly
    0.06
    Leader
    0.06
    orelease
    0.06
     oppon
    0.06
     Adj
    0.06
    Activations Density 0.010%

    No Known Activations