© 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. 30594
    Prev
    Next
    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash

    The neuron activates on the XML plist “<key> … </key>” elements, i.e. it detects the plist key tags (like CFBundle… entries).

    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
     chan
    -0.07
     độc
    -0.07
     loading
    -0.07
     Prod
    -0.06
    _loading
    -0.06
     Survival
    -0.06
     JWT
    -0.06
     fault
    -0.06
    .break
    -0.06
    -less
    -0.06
    POSITIVE LOGITS
     cinemat
    0.06
    ویل
    0.06
     colorWith
    0.06
    �
    0.06
    •↵↵
    0.06
     населення
    0.06
     baj
    0.06
     erotische
    0.06
    $view
    0.06
     Kaynak
    0.06
    Activations Density 0.004%

    No Known Activations