© 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 EvalsExportsinterp-engineNEWAPI 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. 105054
    Prev
    Next
    INDEX
    Explanations

    phrases indicating deception or dishonesty

    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
    ,tp
    -0.07
    ntag
    -0.07
    ovah
    -0.06
    åķı
    -0.06
    trace
    -0.06
     attn
    -0.06
     киÑģ
    -0.06
    boxed
    -0.06
    tml
    -0.06
    cef
    -0.06
    POSITIVE LOGITS
    accur
    0.13
     accurate
    0.12
     truthful
    0.12
     accurately
    0.11
    accuracy
    0.11
     inaccurate
    0.10
     accuracy
    0.10
     truth
    0.10
     verdad
    0.09
     promises
    0.09
    Activations Density 0.077%

    No Known Activations