© 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. 6378
    Prev
    Next
    INDEX
    Explanations

    Locations

    np_max-act · gemini-2.0-flash

    This neuron detects the names of performance venues or locations (e.g. theatres, festivals, cities).

    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
     chua
    -0.06
    CENTER
    -0.06
    271
    -0.06
    开
    -0.06
    ΙΣΤ
    -0.06
    verify
    -0.06
    	com
    -0.06
    Sol
    -0.06
     OSP
    -0.06
    译
    -0.06
    POSITIVE LOGITS
    ISR
    0.06
    .SetString
    0.06
     nặng
    0.06
    emoji
    0.06
    urred
    0.06
    ması
    0.06
     generado
    0.06
     خورد
    0.06
     провести
    0.06
     юрид
    0.06
    Activations Density 0.012%

    No Known Activations