© 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. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 89699
    Prev
    Next
    INDEX
    Explanations

    Nominee

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of official nominations and confirmations—e.g. the word “nominee,” “nomination,” and related tokens around appointing or confirming a person to a government post.

    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
    endale
    -0.06
    Dean
    -0.06
     Neon
    -0.06
    Rent
    -0.06
    заб
    -0.06
    rien
    -0.06
     tally
    -0.06
     neon
    -0.06
     synchronized
    -0.06
     synchron
    -0.06
    POSITIVE LOGITS
    	align
    0.07
    getQuery
    0.07
    (rowIndex
    0.07
    람
    0.06
     května
    0.06
    /store
    0.06
    .Stdout
    0.06
    light
    0.06
    after
    0.06
    ifi
    0.06
    Activations Density 0.015%

    No Known Activations