© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 73564
    Prev
    Next
    INDEX
    Explanations

    elect

    np_max-act · gemini-2.0-flash

    references to political events and leadership changes.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron is triggered by terms related to elections and voting (e.g. “elect,” “elected,” “election”).

    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
     Moh
    -0.06
    Moh
    -0.06
     width
    -0.06
     Iris
    -0.06
    _odd
    -0.06
     break
    -0.06
     Joel
    -0.06
    巨
    -0.06
     tech
    -0.06
     Ginny
    -0.06
    POSITIVE LOGITS
     některých
    0.07
     appoint
    0.07
    ��
    0.07
    Requires
    0.07
    	NdrFcShort
    0.06
     Registers
    0.06
    NT
    0.06
    udging
    0.06
     kültür
    0.06
    _shipping
    0.06
    Activations Density 0.012%

    No Known Activations