© 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. 103397
    Prev
    Next
    INDEX
    Explanations

    concepts related to morality and ethical dilemmas

    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
    .scalablytyped
    -0.08
     microtime
    -0.08
    ÌĨ
    -0.07
    afi
    -0.07
    sonian
    -0.07
     Ø·ÙĦ
    -0.07
    /lists
    -0.07
    ãĥ©ãĤ¹
    -0.07
    .ali
    -0.07
    æ®
    -0.07
    POSITIVE LOGITS
    aye
    0.07
     merc
    0.06
    康
    0.06
    åħ°
    0.06
     ev
    0.06
    _OVERFLOW
    0.06
     capit
    0.05
    gi
    0.05
     rect
    0.05
    Forg
    0.05
    Activations Density 0.005%

    No Known Activations