© 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. 15-LLAMASCOPE-RES-131K
    11. 104251
    Prev
    Next
    INDEX
    Explanations

    references to positions and roles within the Communist Party

    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
    utex
    -0.07
     Walker
    -0.07
    otos
    -0.07
    ãĥĢãĥ¼
    -0.06
    UBY
    -0.06
    оÑĢдин
    -0.06
    urette
    -0.06
    eydi
    -0.06
    pgsql
    -0.06
     Damon
    -0.06
    POSITIVE LOGITS
    505
    0.07
    redient
    0.06
    aren
    0.06
    atical
    0.06
    ør
    0.06
     nhu
    0.06
     Clubs
    0.06
    ãĥ³ãĤ¹
    0.06
    ione
    0.06
     Yugosl
    0.06
    Activations Density 0.008%

    No Known Activations