© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 125051
    Prev
    Next
    INDEX
    Explanations

    brackets/parentheses

    np_max-act · gemini-2.0-flash

    This neuron fires on code‐style syntax (e.g. class and def declarations, method names with self, parentheses, and indentation) in the assistant’s examples.

    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
     Место
    -0.06
    ยาย
    -0.06
     nào
    -0.06
     ice
    -0.06
    greater
    -0.06
    ièrement
    -0.06
    dry
    -0.06
     wastewater
    -0.06
    男
    -0.06
     бач
    -0.06
    POSITIVE LOGITS
    addEventListener
    0.06
    .ContainsKey
    0.06
    .Information
    0.06
    JJ
    0.06
    ังก
    0.06
     ".$_
    0.06
    								 
    0.06
     Alex
    0.06
     rename
    0.06
     olmadığı
    0.06
    Activations Density 0.020%

    No Known Activations