© 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. 70745
    Prev
    Next
    INDEX
    Explanations

    mentions of organizations, governmental bodies, or regulatory entities

    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
    irtual
    -0.07
     Vernon
    -0.07
    elib
    -0.07
     Ellison
    -0.06
    unnel
    -0.06
    ầm
    -0.06
     eo
    -0.06
    abling
    -0.06
     poz
    -0.06
    ÐŁÐ¾Ñģ
    -0.06
    POSITIVE LOGITS
    ldr
    0.07
    AREST
    0.06
    .libs
    0.06
    istr
    0.06
    \Php
    0.06
    miner
    0.06
    аниÑĨ
    0.06
    HeaderCode
    0.06
    \Blueprint
    0.06
    531
    0.06
    Activations Density 0.001%

    No Known Activations