© 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. 30003
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases indicating continuity or connection

    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
    awi
    -0.07
    onne
    -0.06
    pler
    -0.06
     Brent
    -0.06
     Lia
    -0.06
     Ronald
    -0.06
    ìĸij
    -0.06
    ensi
    -0.06
    ylon
    -0.06
     Appointment
    -0.06
    POSITIVE LOGITS
     throughout
    0.09
    .scalablytyped
    0.09
     beyond
    0.09
    GenerationStrategy
    0.07
    during
    0.07
    vous
    0.07
     Beyond
    0.07
    oại
    0.07
    (Cs
    0.07
    _ptrs
    0.07
    Activations Density 0.061%

    No Known Activations