© 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. 127627
    Prev
    Next
    INDEX
    Explanations

    phrases that reflect personal experiences and self-awareness

    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
    iversit
    -0.09
    apl
    -0.08
    otify
    -0.06
    å®
    -0.06
    asca
    -0.06
     live
    -0.06
    aña
    -0.06
    ê¹
    -0.06
     post
    -0.06
    uw
    -0.06
    POSITIVE LOGITS
     playing
    0.07
    boy
    0.07
     Development
    0.07
     vex
    0.06
    ODEV
    0.06
    /utility
    0.06
    ardy
    0.06
     développ
    0.06
    RICT
    0.06
     lokale
    0.06
    Activations Density 0.002%

    No Known Activations