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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 117316
    Prev
    Next
    INDEX
    Explanations

    expressions related to home improvement or flooring projects

    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
    ожд
    -0.06
     Michaels
    -0.06
    NavItem
    -0.06
    occo
    -0.06
    å¹¹
    -0.06
     æľĿ
    -0.06
    _mp
    -0.06
    amento
    -0.06
    MS
    -0.06
     smo
    -0.06
    POSITIVE LOGITS
    ubby
    0.06
     erg
    0.06
     Cust
    0.06
    illon
    0.06
     bal
    0.06
    alin
    0.06
    ade
    0.05
     addCriterion
    0.05
    rium
    0.05
    ξι
    0.05
    Activations Density 0.001%

    No Known Activations