© 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. 77801
    Prev
    Next
    INDEX
    Explanations

    conjunctions indicating contrast or conjunction in arguments

    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
    .DOM
    -0.08
    енз
    -0.07
    atis
    -0.07
    ctp
    -0.07
     å®
    -0.07
     tròn
    -0.07
    hausen
    -0.06
    à¥įयप
    -0.06
    stit
    -0.06
    elib
    -0.06
    POSITIVE LOGITS
    apesh
    0.07
     this
    0.07
     This
    0.07
    This
    0.07
    è¿Ļæĺ¯
    0.07
     despite
    0.06
    rog
    0.06
    amentos
    0.06
     most
    0.06
    rogen
    0.06
    Activations Density 0.007%

    No Known Activations