© 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. 18
    Prev
    Next
    INDEX
    Explanations

    references to events or announcements in a series

    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
     indirectly
    -0.06
    ers
    -0.06
    iks
    -0.05
    âĢ¦↵
    -0.05
    erman
    -0.05
     Prototype
    -0.05
     whe
    -0.05
     immediately
    -0.05
    âĢ¦
    -0.05
     prototype
    -0.05
    POSITIVE LOGITS
    /stretch
    0.09
    ulty
    0.09
    uela
    0.08
     povol
    0.08
    iglia
    0.08
    ÐĶÐIJ
    0.07
    .scalablytyped
    0.07
    éłĨ
    0.07
    ÑĤÑı
    0.07
     addCriterion
    0.07
    Activations Density 0.009%

    No Known Activations