© 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. 39819
    Prev
    Next
    INDEX
    Explanations

    action-oriented phrases encouraging participation or engagement

    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
    rap
    -0.07
     ---------------------------------------------------------------------------↵
    -0.06
    Donate
    -0.06
    untime
    -0.06
    γÏĮ
    -0.05
    ewire
    -0.05
    ores
    -0.05
    лаж
    -0.05
     Donate
    -0.05
    arna
    -0.05
    POSITIVE LOGITS
    試
    0.08
    adan
    0.08
    ucha
    0.07
     join
    0.07
    вад
    0.07
    LIK
    0.07
     start
    0.07
    join
    0.07
     try
    0.07
     starts
    0.07
    Activations Density 0.025%

    No Known Activations