© 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. 4180
    Prev
    Next
    INDEX
    Explanations

    elements related to governance, administrative structuring, and legal frameworks

    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
    loff
    -0.07
    erras
    -0.06
    ittal
    -0.06
    âĢİ
    -0.06
    ungle
    -0.06
    ays
    -0.05
     scor
    -0.05
    ured
    -0.05
     coordin
    -0.05
    âĢª
    -0.05
    POSITIVE LOGITS
    ̧
    0.07
    inium
    0.07
    ogram
    0.07
    nelly
    0.07
    rup
    0.07
    ä»ĭ
    0.07
    .uc
    0.06
    venida
    0.06
    iyon
    0.06
    amburger
    0.06
    Activations Density 0.128%

    No Known Activations