© 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. 58148
    Prev
    Next
    INDEX
    Explanations

    terms related to universality and universal rights

    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
    eka
    -0.08
    yonel
    -0.07
    chen
    -0.07
    usc
    -0.07
    ela
    -0.07
    esar
    -0.07
    oret
    -0.07
    ãĥĥãĥģ
    -0.07
    leton
    -0.07
    akan
    -0.07
    POSITIVE LOGITS
    ized
    0.10
    ize
    0.09
    izing
    0.09
    ised
    0.09
    /global
    0.09
    ities
    0.08
    ist
    0.08
    /un
    0.08
    -scale
    0.08
    å®Ļ
    0.07
    Activations Density 0.007%

    No Known Activations