Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 55303
    Prev
    Next
    INDEX
    Explanations

    god

    np_max-act · gemini-2.0-flash

    This neuron specifically detects mentions of deities (e.g. “gods,” “goddess,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     러
    -0.06
     Keystone
    -0.06
     PHPUnit
    -0.06
     known
    -0.06
    externalActionCode
    -0.06
    .registration
    -0.06
    	arg
    -0.06
     mạch
    -0.06
    (delay
    -0.06
    ehicle
    -0.06
    POSITIVE LOGITS
     gods
    0.08
     Gods
    0.07
     goddess
    0.07
    ψη
    0.06
    andi
    0.06
    .Services
    0.06
     Goddess
    0.06
    SS
    0.06
    secure
    0.06
    exclude
    0.06
    Activations Density 0.008%

    No Known Activations