© 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. 107053
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming constructs related to defining and manipulating data structures

    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
    ongyang
    -0.09
    sans
    -0.09
    ogr
    -0.08
    eyse
    -0.08
     taxp
    -0.08
    áºŃy
    -0.08
    ॰
    -0.07
    ụy
    -0.07
    ovy
    -0.07
    WITHOUT
    -0.07
    POSITIVE LOGITS
    Ŀ
    0.06
    âĢ¯
    0.05
     sust
    0.05
    Âł
    0.05
    ango
    0.05
    ke
    0.05
    cher
    0.05
     lip
    0.05
    SI
    0.05
     Likewise
    0.05
    Activations Density 0.156%

    No Known Activations