© 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. 83594
    Prev
    Next
    INDEX
    Explanations

    references to academic essays or scholarly articles

    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
     r
    -0.06
     d
    -0.06
    âĢ¦
    -0.06
     train
    -0.06
     _
    -0.06
     forward
    -0.05
     job
    -0.05
     Union
    -0.05
     Ein
    -0.05
    illard
    -0.05
    POSITIVE LOGITS
    Äįel
    0.10
     ÙħÙĪب
    0.09
     gó
    0.09
     nackte
    0.08
    avr
    0.08
    rand
    0.08
    inue
    0.08
     MÄĽst
    0.08
    eyse
    0.08
     chó
    0.08
    Activations Density 0.017%

    No Known Activations