© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 22-LLAMASCOPE-RES-131K
    11. 4157
    Prev
    Next
    INDEX
    Explanations

    references to architecture and design concepts in network systems

    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
    .scalablytyped
    -0.09
    MLE
    -0.07
     imagin
    -0.07
    .TestTools
    -0.07
    mez
    -0.06
     sple
    -0.06
    tru
    -0.06
    bpp
    -0.06
    chg
    -0.06
    acz
    -0.06
    POSITIVE LOGITS
     внÑĥ
    0.07
    .twitch
    0.07
     designer
    0.07
     upto
    0.07
     ìĤ
    0.07
     design
    0.06
    iena
    0.06
     datap
    0.06
    -runtime
    0.06
     fully
    0.06
    Activations Density 0.002%

    No Known Activations