© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 84200
    Prev
    Next
    INDEX
    Explanations

    references to legal actions or liabilities within contractual 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
    apot
    -0.07
    redd
    -0.07
    reet
    -0.07
    Îĸ
    -0.07
    uibModal
    -0.07
    غات
    -0.07
     sobie
    -0.06
     yap
    -0.06
    earch
    -0.06
    Ïģοι
    -0.06
    POSITIVE LOGITS
    idon
    0.07
    ÐŁÐļ
    0.06
    uire
    0.06
    iddy
    0.06
     joint
    0.06
     sue
    0.06
    æij©
    0.06
    534
    0.06
    ville
    0.06
    blers
    0.06
    Activations Density 0.002%

    No Known Activations