© 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. 118308
    Prev
    Next
    INDEX
    Explanations

    terms related to legal documents and citations

    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
    _MC
    -0.06
    andon
    -0.06
    arella
    -0.06
    usiness
    -0.06
     Obr
    -0.06
    اض
    -0.06
     Nack
    -0.06
    ÙıÙĪÙĨ
    -0.05
    ocos
    -0.05
     DÃŃky
    -0.05
    POSITIVE LOGITS
    ensch
    0.06
    fork
    0.06
    igua
    0.06
    ãĥ³ãĥĸ
    0.06
    â
    0.06
     CommandType
    0.06
    ugu
    0.06
     crossorigin
    0.06
    .BorderFactory
    0.06
    hoe
    0.06
    Activations Density 0.003%

    No Known Activations