© 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. 82347
    Prev
    Next
    INDEX
    Explanations

    references to censorship and the regulation of content

    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
    è¡Ĩ
    -0.08
    ãi
    -0.08
    ittel
    -0.07
    .env
    -0.07
     Tub
    -0.07
    Trap
    -0.06
    ниÑĩ
    -0.06
    olik
    -0.06
    à¥Ĥद
    -0.06
    ported
    -0.06
    POSITIVE LOGITS
     schools
    0.07
     Schools
    0.07
    htdocs
    0.06
     parental
    0.06
     Narrative
    0.06
    alous
    0.06
     Hunter
    0.06
    asd
    0.06
    odb
    0.06
     Zucker
    0.06
    Activations Density 0.004%

    No Known Activations