© 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. 118743
    Prev
    Next
    INDEX
    Explanations

    concepts related to selling and integrity in the context of moral or ethical dilemmas

    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
    ings
    -0.07
    .builders
    -0.07
    oux
    -0.07
    rof
    -0.07
    δί
    -0.07
    .documentation
    -0.06
    fsp
    -0.06
    kara
    -0.06
    zem
    -0.06
    .inflate
    -0.06
    POSITIVE LOGITS
     sell
    0.10
     Sell
    0.08
     selling
    0.08
    sell
    0.08
    Sell
    0.07
     sells
    0.07
     Selling
    0.07
    HEST
    0.07
    302
    0.06
     sold
    0.06
    Activations Density 0.016%

    No Known Activations