© 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. 86888
    Prev
    Next
    INDEX
    Explanations

    topics related to public health and safety concerns

    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
    lege
    -0.06
     brat
    -0.06
    ales
    -0.06
    iolet
    -0.06
     contempor
    -0.06
    arem
    -0.06
     dates
    -0.06
    ournal
    -0.06
    923
    -0.06
    485
    -0.06
    POSITIVE LOGITS
     overall
    0.07
    ocu
    0.07
     throughout
    0.07
    zu
    0.07
     several
    0.07
    overall
    0.07
    еÑĢап
    0.06
    StackNavigator
    0.06
     answers
    0.06
    akov
    0.06
    Activations Density 0.015%

    No Known Activations