© 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. 70418
    Prev
    Next
    INDEX
    Explanations

    instances of deception and manipulation related to job hiring and medical practices

    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
    illy
    -0.07
    yx
    -0.07
    ucci
    -0.07
     Miner
    -0.06
    ãĥĥ
    -0.06
    /GPL
    -0.06
    acl
    -0.06
    Insensitive
    -0.06
    kus
    -0.06
     incompetent
    -0.06
    POSITIVE LOGITS
     faker
    0.13
     fake
    0.13
     fraud
    0.12
     fraudulent
    0.11
     fals
    0.11
     Fraud
    0.10
     Fake
    0.10
     che
    0.10
     frau
    0.10
     false
    0.09
    Activations Density 0.130%

    No Known Activations