© 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. 109370
    Prev
    Next
    INDEX
    Explanations

    code queries

    np_max-act · gemini-2.0-flash

    This neuron detects references to a “filter” parameter and its use in conditional statements for adding query constraints.

    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
     sou
    -0.07
     Islands
    -0.07
     woods
    -0.07
    μως
    -0.07
     Hills
    -0.06
     bounce
    -0.06
    	object
    -0.06
    (cal
    -0.06
     نوشته
    -0.06
     mould
    -0.06
    POSITIVE LOGITS
    รายการ
    0.06
     Famil
    0.06
     него
    0.06
    //{↵
    0.06
     seiz
    0.06
    ');?>"
    0.06
    ]));↵↵
    0.06
    <select
    0.05
    ζί
    0.05
    jure
    0.05
    Activations Density 0.023%

    No Known Activations