© 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. 55298
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to evidence in a trial context

    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
    jak
    -0.07
    ãĥ¼ãĥĦ
    -0.07
     createAction
    -0.06
     pasar
    -0.06
    stadt
    -0.06
    anio
    -0.06
     vũ
    -0.06
     stead
    -0.06
     ja
    -0.06
    Ñĥмов
    -0.06
    POSITIVE LOGITS
     discovery
    0.09
     Discovery
    0.08
    voir
    0.07
    Discovery
    0.07
     Mime
    0.06
     Carp
    0.06
    yon
    0.06
     Weiner
    0.06
    uckland
    0.06
     discoveries
    0.06
    Activations Density 0.004%

    No Known Activations