© 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. 17-LLAMASCOPE-RES-131K
    11. 3141
    Prev
    Next
    INDEX
    Explanations

    components related to historical or geographical context

    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
     multiple
    -0.06
    immel
    -0.06
    bee
    -0.06
     denen
    -0.05
    ectl
    -0.05
     Gib
    -0.05
    ий
    -0.05
    ptom
    -0.05
    %C
    -0.05
    86
    -0.05
    POSITIVE LOGITS
    該
    0.10
    ãģĵãģ®
    0.09
    该
    0.09
    otel
    0.08
    nces
    0.07
     project
    0.07
     íķ´ëĭ¹
    0.07
    abei
    0.07
    æѤ
    0.07
    sut
    0.07
    Activations Density 0.037%

    No Known Activations