© 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. 17880
    Prev
    Next
    INDEX
    Explanations

    themes related to moral dilemmas and character relationships

    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
    deÅŁ
    -0.07
     waiver
    -0.07
    _por
    -0.07
    ÃĹ↵↵
    -0.07
    pora
    -0.07
    LIK
    -0.07
    ç¹Ķ
    -0.07
    رش
    -0.07
     Kont
    -0.07
    xFFFFFFFF
    -0.07
    POSITIVE LOGITS
    idel
    0.07
     missions
    0.07
     mission
    0.06
    allet
    0.06
    mour
    0.06
    uin
    0.06
     Freel
    0.06
     save
    0.06
     artificially
    0.06
     nhiá»ĩm
    0.05
    Activations Density 0.043%

    No Known Activations