© 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. 58072
    Prev
    Next
    INDEX
    Explanations

    HTML tags and attributes

    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
     surplus
    -0.06
     bapt
    -0.06
    ness
    -0.06
     APK
    -0.06
    aç
    -0.05
    еп
    -0.05
     impeachment
    -0.05
     mechan
    -0.05
    lish
    -0.05
     apolog
    -0.05
    POSITIVE LOGITS
    zych
    0.09
    actionDate
    0.08
    ystems
    0.08
     ResourceType
    0.07
    arResult
    0.07
    .RunWith
    0.07
     "[%
    0.07
    oup
    0.07
    /Area
    0.07
    anch
    0.07
    Activations Density 0.015%

    No Known Activations