© 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
    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. 110607
    Prev
    Next
    INDEX
    Explanations

    owed

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on words in their simple past (regular) verb form, i.e. verbs ending in “-ed.”

    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
    ْر
    -0.06
    InnerText
    -0.06
    -metal
    -0.06
    ditor
    -0.06
    нии
    -0.06
    िच
    -0.06
    CLOSE
    -0.06
    _CheckedChanged
    -0.06
    。これ
    -0.06
    사회
    -0.06
    POSITIVE LOGITS
     значительно
    0.07
     viel
    0.07
     -.
    0.07
     полностью
    0.06
     blowjob
    0.06
     kön
    0.06
    .stride
    0.06
     Guzzle
    0.06
     باد
    0.06
    0.06
    Activations Density 0.106%

    No Known Activations