© 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 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. 15-LLAMASCOPE-RES-131K
    11. 88793
    Prev
    Next
    INDEX
    Explanations

    phrases indicating promotions and deals

    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
    anne
    -0.07
    rol
    -0.06
     rub
    -0.06
     Em
    -0.05
    ãģ¾ãĤĭ
    -0.05
     em
    -0.05
     Ade
    -0.05
    ÑĢоÑĪ
    -0.05
     next
    -0.05
    iss
    -0.05
    POSITIVE LOGITS
     eoq
    0.09
    /WebAPI
    0.08
     огÑĢа
    0.08
     Stocks
    0.08
    asics
    0.07
    SpaceItem
    0.07
    .MixedReality
    0.07
    943
    0.07
     overposting
    0.07
    .SizeType
    0.07
    Activations Density 0.000%

    No Known Activations