© 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. 85128
    Prev
    Next
    INDEX
    Explanations

    references to perceived moral or ethical issues

    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
    XL
    -0.07
    é¦Ļ
    -0.07
     pog
    -0.07
    äºĮ人
    -0.06
    #__
    -0.06
    encia
    -0.06
    phies
    -0.06
    lun
    -0.06
     vic
    -0.06
    ÙĪÛĮÛĮ
    -0.06
    POSITIVE LOGITS
    ://%
    0.07
    uxtap
    0.07
    LabelText
    0.07
    ales
    0.07
     Washing
    0.06
     closely
    0.06
     washing
    0.06
     Trou
    0.06
    oultry
    0.06
    ://'
    0.06
    Activations Density 0.017%

    No Known Activations