© 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. 108543
    Prev
    Next
    INDEX
    Explanations

    references to nodes and vertices in a graph or network structure

    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
    -minded
    -0.10
    ner
    -0.09
    mente
    -0.08
    loh
    -0.08
    coni
    -0.08
    nga
    -0.08
    ly
    -0.08
    los
    -0.08
    JOR
    -0.08
    mer
    -0.08
    POSITIVE LOGITS
    fault
    0.10
    ules
    0.08
    owner
    0.08
    hood
    0.07
    chef
    0.07
    FAULT
    0.07
    hunter
    0.07
    /system
    0.07
    frey
    0.06
    izens
    0.06
    Activations Density 0.027%

    No Known Activations