© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 26890
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to possession and exorcism

    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
    ocaly
    -0.09
    esty
    -0.08
     lòng
    -0.08
     xúc
    -0.07
    odge
    -0.07
    erva
    -0.07
    WI
    -0.06
    okies
    -0.06
    onis
    -0.06
    yr
    -0.06
    POSITIVE LOGITS
    otron
    0.08
     Tradable
    0.07
     Carp
    0.06
    di
    0.06
     pylint
    0.06
     battle
    0.05
    deo
    0.05
    ë
    0.05
    pedia
    0.05
     LIN
    0.05
    Activations Density 0.012%

    No Known Activations