© 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. 9-LLAMASCOPE-RES-131K
    11. 97694
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to sin and moral judgment

    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
    åŀ
    -0.07
    quo
    -0.07
    ÙħاÙĦ
    -0.07
    endencies
    -0.07
    ADER
    -0.07
    ixin
    -0.06
    entai
    -0.06
    ckett
    -0.06
    enders
    -0.06
    agit
    -0.06
    POSITIVE LOGITS
    uous
    0.07
     å·´
    0.07
    fully
    0.07
    rf
    0.07
    de
    0.06
    linger
    0.06
    -death
    0.06
    аÐ
    0.06
    çķ
    0.06
    /problem
    0.06
    Activations Density 0.011%

    No Known Activations