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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 105764
    Prev
    Next
    INDEX
    Explanations

    Travel destinations

    np_max-act · gemini-2.0-flash

    cultural and historical information about cities.

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

    the neuron detects descriptive, attribute-highlighting language—especially adjectives and phrases used to promote or summarize the qualities of a city.

    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
     careers
    -0.07
    _API
    -0.07
    icontrol
    -0.07
    wal
    -0.07
    oval
    -0.07
    βο
    -0.06
     bu
    -0.06
     AR
    -0.06
    еты
    -0.06
    투
    -0.06
    POSITIVE LOGITS
     حالة
    0.07
    RESULT
    0.06
    ULER
    0.06
    احل
    0.06
    plits
    0.06
     Specification
    0.06
    ــــ
    0.06
     Raise
    0.06
     پرونده
    0.06
    voj
    0.06
    Activations Density 0.066%

    No Known Activations