© 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. 78960
    Prev
    Next
    INDEX
    Explanations

    references to applications in scientific fields

    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
     Wash
    -0.06
    egra
    -0.06
     int
    -0.06
     wash
    -0.06
     sic
    -0.06
    oder
    -0.05
    oran
    -0.05
    _ln
    -0.05
     bay
    -0.05
     exc
    -0.05
    POSITIVE LOGITS
     applications
    0.12
     Applications
    0.10
    applications
    0.10
    Applications
    0.09
    пÑĢиклад
    0.09
     situations
    0.08
    âĸį
    0.07
     contexts
    0.07
    ırak
    0.07
    aggi
    0.07
    Activations Density 0.030%

    No Known Activations