© 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. 16998
    Prev
    Next
    INDEX
    Explanations

    programming constructs and operations involving data handling

    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
     starter
    -0.06
     Cad
    -0.06
     pled
    -0.06
     cad
    -0.06
     pus
    -0.06
    starter
    -0.06
     Starter
    -0.06
     Valent
    -0.06
     kon
    -0.05
     STM
    -0.05
    POSITIVE LOGITS
     report
    0.12
     Report
    0.10
     results
    0.10
     reports
    0.09
    report
    0.09
     overall
    0.09
    Report
    0.09
     REPORT
    0.09
     performance
    0.08
     reported
    0.08
    Activations Density 0.030%

    No Known Activations