© 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. 15-LLAMASCOPE-RES-131K
    11. 1360
    Prev
    Next
    INDEX
    Explanations

    phrases related to claims of deception or falsehoods

    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
    rott
    -0.09
    ấp
    -0.08
    hi
    -0.07
    rone
    -0.07
    ormsg
    -0.06
    rani
    -0.06
     Markus
    -0.06
    ami
    -0.06
    erk
    -0.06
    atz
    -0.06
    POSITIVE LOGITS
    LY
    0.08
    ment
    0.07
    ly
    0.07
    mente
    0.07
    ewis
    0.07
    edList
    0.06
    oux
    0.06
    ôm
    0.06
    ably
    0.06
     (?)
    0.06
    Activations Density 0.013%

    No Known Activations