© 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. 40015
    Prev
    Next
    INDEX
    Explanations

    concepts of comparison and relationships among entities

    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
    vit
    -0.07
     hack
    -0.06
    s
    -0.06
    Hack
    -0.06
    rad
    -0.06
    ul
    -0.06
    mgr
    -0.06
     obce
    -0.05
    entine
    -0.05
     moto
    -0.05
    POSITIVE LOGITS
    -même
    0.10
    ipsis
    0.08
    دÛĮگر
    0.08
    .scalablytyped
    0.07
    hores
    0.07
    exels
    0.07
    Cancelable
    0.07
    elves
    0.07
     themselves
    0.07
    /by
    0.07
    Activations Density 0.009%

    No Known Activations