© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 44499
    Prev
    Next
    INDEX
    Explanations

    object

    np_max-act · gemini-2.0-flash

    The neuron detects Python exception message patterns, especially the “'X' object has no attribute 'Y'” wording.

    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
    ्व
    -0.07
    ินเด
    -0.06
    igate
    -0.06
    essa
    -0.06
     overd
    -0.06
    ){↵↵
    -0.06
    IDDLE
    -0.06
     winter
    -0.06
    สต
    -0.06
    igel
    -0.06
    POSITIVE LOGITS
     способ
    0.07
    (/
    0.06
    ‐‐
    0.06
    UIBarButtonItem
    0.06
    kube
    0.06
     Bakery
    0.06
     army
    0.06
     tablespoon
    0.06
     imagined
    0.06
     ''
    0.06
    Activations Density 0.007%

    No Known Activations