© 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. 83407
    Prev
    Next
    INDEX
    Explanations

    programming and data structure elements related to constraints and exceptions

    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
    rale
    -0.07
    reu
    -0.07
     synd
    -0.06
    mlin
    -0.06
     sint
    -0.06
    lep
    -0.06
    rana
    -0.06
    enne
    -0.06
     Synd
    -0.06
    raits
    -0.06
    POSITIVE LOGITS
    asic
    0.07
    alex
    0.07
    ignon
    0.07
    SizePolicy
    0.06
    IOC
    0.06
    THR
    0.06
    rogen
    0.06
    idel
    0.06
     пÑĢием
    0.06
    åĪ°åºķ
    0.06
    Activations Density 0.005%

    No Known Activations