© 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 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. 29013
    Prev
    Next
    INDEX
    Explanations

    references to supernatural entities and beliefs in demons

    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
    ulture
    -0.07
    vais
    -0.07
     Hers
    -0.06
    redict
    -0.06
    ickerView
    -0.06
    민
    -0.06
    hesive
    -0.06
    ominator
    -0.06
    alfa
    -0.06
    _EXPORT
    -0.06
    POSITIVE LOGITS
     existence
    0.18
     exist
    0.15
     reality
    0.15
     Exist
    0.15
     exists
    0.15
    existence
    0.14
    åŃĺåľ¨
    0.13
     real
    0.13
    Exist
    0.13
     Exists
    0.13
    Activations Density 0.103%

    No Known Activations