© 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. 75999
    Prev
    Next
    INDEX
    Explanations

    terms related to hypocrisy and critical accusations

    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
    rada
    -0.07
    pa
    -0.07
    Interop
    -0.07
    пеÑĩ
    -0.07
    iners
    -0.07
    _IMP
    -0.07
    geb
    -0.07
    lier
    -0.06
    antz
    -0.06
    lé
    -0.06
    POSITIVE LOGITS
    ically
    0.08
    ical
    0.08
    emia
    0.07
    ity
    0.07
    ocrisy
    0.07
     nature
    0.07
    /self
    0.07
    571
    0.06
    idal
    0.06
    271
    0.06
    Activations Density 0.001%

    No Known Activations