© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 27772
    Prev
    Next
    INDEX
    Explanations

    programming concepts related to data structures, particularly trees and nodes

    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
    aroo
    -0.08
    ircon
    -0.07
     पड
    -0.07
    oulouse
    -0.07
    cela
    -0.07
    wnd
    -0.07
    аÑĤом
    -0.07
    athon
    -0.07
    /window
    -0.07
    nga
    -0.07
    POSITIVE LOGITS
     leaf
    0.10
     Leaf
    0.09
     tree
    0.09
     node
    0.08
     subtree
    0.08
     деÑĢева
    0.08
    leaf
    0.08
    (tree
    0.08
     root
    0.08
    node
    0.07
    Activations Density 0.014%

    No Known Activations