© 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. 565
    Prev
    Next
    INDEX
    Explanations

    census, location data

    np_max-act · gemini-2.0-flash

    This neuron detects the phrasing used to report demographic change—specifically the “up … from …” population‐increase statements in census write-ups.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    information related to demographic data and historical context of towns or cities.

    oai_token-act-pair · gpt-4o-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
    ables
    -0.07
    fully
    -0.06
    attack
    -0.06
    	div
    -0.06
     printed
    -0.06
    زار
    -0.06
     rés
    -0.06
     Quit
    -0.05
    .prob
    -0.05
     Wisdom
    -0.05
    POSITIVE LOGITS
    .setEnabled
    0.07
    üncü
    0.07
     ülkenin
    0.07
     scr
    0.07
     DevExpress
    0.06
    arı
    0.06
     Academ
    0.06
     explos
    0.06
    (handles
    0.06
    generic
    0.06
    Activations Density 0.007%

    No Known Activations