© 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. 9-LLAMASCOPE-RES-131K
    11. 95758
    Prev
    Next
    INDEX
    Explanations

    prepositions and phrases denoting relationships or connections

    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
    ÏĢοÏį
    -0.07
    .googleapis
    -0.07
    ÑĥÑĢн
    -0.07
    âĢ¦↵↵↵
    -0.07
    ekim
    -0.07
    нез
    -0.07
    iddet
    -0.06
     Anch
    -0.06
    ellan
    -0.06
     McCart
    -0.06
    POSITIVE LOGITS
    æĹ
    0.06
    IJëĭ¤
    0.06
    omi
    0.06
    icles
    0.05
    enga
    0.05
    ï¼Īå¹³æĪIJ
    0.05
    illaume
    0.05
    \Migration
    0.05
    uzzi
    0.05
    INCREMENT
    0.05
    Activations Density 0.004%

    No Known Activations