© 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. 89775
    Prev
    Next
    INDEX
    Explanations

    foreign verbs

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on German infinitive verbs ending in “-ieren.”

    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
    -0.07
     rode
    -0.07
    ovaná
    -0.07
    Tags
    -0.06
     biking
    -0.06
     Dude
    -0.06
     completa
    -0.06
     wreckage
    -0.06
    ang
    -0.06
     Cemetery
    -0.06
    POSITIVE LOGITS
    하기
    0.08
    する
    0.08
    ßen
    0.07
    달
    0.07
    -playing
    0.07
     sağlamak
    0.07
    ging
    0.07
    рабат
    0.07
    pcm
    0.07
    える
    0.07
    Activations Density 0.042%

    No Known Activations