© 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. 70594
    Prev
    Next
    INDEX
    Explanations

    quantities or references to multiple items or quantities

    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
     stuff
    -0.09
    stuff
    -0.08
    aries
    -0.07
    jen
    -0.07
    ries
    -0.07
     же
    -0.07
    agnost
    -0.07
    ling
    -0.07
    ihn
    -0.07
    orem
    -0.07
    POSITIVE LOGITS
    /all
    0.10
     of
    0.09
     persons
    0.08
    usc
    0.07
     dozen
    0.07
    ToOne
    0.07
    ollywood
    0.07
     additional
    0.06
     Persons
    0.06
     depending
    0.06
    Activations Density 0.012%

    No Known Activations