© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 83887
    Prev
    Next
    INDEX
    Explanations

    references to legal issues and specific case details related to defamation

    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
     humanitarian
    -0.07
    fcn
    -0.07
    QUEST
    -0.07
    ignant
    -0.06
     Homework
    -0.06
    úi
    -0.06
    ething
    -0.06
    issors
    -0.06
     cri
    -0.06
    andbox
    -0.06
    POSITIVE LOGITS
     Campus
    0.08
     campus
    0.08
    BuilderInterface
    0.07
    andr
    0.07
     freedom
    0.07
    ONTAL
    0.07
    -campus
    0.07
    ellar
    0.07
     mat
    0.07
     Freedom
    0.07
    Activations Density 0.001%

    No Known Activations