© 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. 128280
    Prev
    Next
    INDEX
    Explanations

    HTML elements and attributes related to navigation links

    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
    ARSE
    -0.07
    å¶
    -0.07
    ttp
    -0.07
    ĴĮ
    -0.07
    лом
    -0.06
    TK
    -0.06
    aign
    -0.06
    oš
    -0.06
    ::*
    -0.06
    Helpers
    -0.06
    POSITIVE LOGITS
     Cove
    0.06
    ulist
    0.06
    cest
    0.06
    084
    0.06
    alat
    0.06
     docking
    0.06
    andin
    0.06
     Luc
    0.05
    iguiente
    0.05
    wik
    0.05
    Activations Density 0.012%

    No Known Activations