© 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. 94509
    Prev
    Next
    INDEX
    Explanations

    phrases reflecting complexity or detail in descriptions

    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
     Vern
    -0.06
     somebody
    -0.06
    .INSTANCE
    -0.06
    é²ľ
    -0.05
    804
    -0.05
     Opportunity
    -0.05
    formats
    -0.05
     M
    -0.05
     Sk
    -0.05
    usher
    -0.05
    POSITIVE LOGITS
    llen
    0.09
    adors
    0.07
    ivent
    0.07
    iedy
    0.07
    κÏģι
    0.07
    aspect
    0.07
    isbury
    0.07
    ayette
    0.07
    iesta
    0.07
    ανά
    0.07
    Activations Density 0.030%

    No Known Activations