© 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. 84780
    Prev
    Next
    INDEX
    Explanations

    structural elements of scientific papers

    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
    BaseContext
    -0.07
    leo
    -0.07
    ampus
    -0.06
    lep
    -0.06
    /*@
    -0.06
    loh
    -0.06
    podob
    -0.06
    Logic
    -0.06
    ierarchy
    -0.06
    dej
    -0.06
    POSITIVE LOGITS
    ibel
    0.07
    æı
    0.07
    ddit
    0.07
    Prov
    0.07
    robat
    0.06
     Prov
    0.06
    -class
    0.06
    atsapp
    0.06
    ên
    0.06
    êm
    0.06
    Activations Density 0.014%

    No Known Activations