© 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. 73597
    Prev
    Next
    INDEX
    Explanations

    _name

    np_max-act · gemini-2.0-flash

    This neuron mainly detects occurrences of the “related_name” argument in Django model field definitions.

    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
     zoals
    -0.07
    ​​
    -0.07
    "The
    -0.07
     Doch
    -0.07
    顔を
    -0.07
     cruc
    -0.06
     skies
    -0.06
    startswith
    -0.06
     जबक
    -0.06
    不知
    -0.06
    POSITIVE LOGITS
     Settings
    0.07
     Information
    0.07
    향
    0.06
     ngoại
    0.06
    -----------
    0.06
     mortgage
    0.06
    pun
    0.06
    (targetEntity
    0.06
    ----------
    0.06
     �
    0.06
    Activations Density 0.001%

    No Known Activations