© 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. 75881
    Prev
    Next
    INDEX
    Explanations

    terms and definitions related to age and eligibility criteria in legal contexts

    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
     â
    -0.06
    cker
    -0.06
    rung
    -0.06
    ieber
    -0.06
    Å¡ti
    -0.06
     correspond
    -0.06
    каÑĢ
    -0.06
     god
    -0.06
    815
    -0.06
    lag
    -0.06
    POSITIVE LOGITS
     shall
    0.07
    аниÑĨ
    0.07
    .Restr
    0.07
    ModelProperty
    0.07
    folio
    0.06
    دÙĪد
    0.06
    ạp
    0.06
     qr
    0.06
     goose
    0.06
    çį¨
    0.06
    Activations Density 0.018%

    No Known Activations