© 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. 44497
    Prev
    Next
    INDEX
    Explanations

    essay writing

    np_max-act · gemini-2.0-flash

    The neuron activates on structured prompt metadata referring to “IELTS Writing Task” labels (e.g. “IELTS,” “writing,” “Task,” plus task numbers).

    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
     odpově
    -0.06
    _<
    -0.06
     disruptions
    -0.06
     Πα
    -0.06
     öğrenc
    -0.06
    飯
    -0.06
     تحص
    -0.06
    غان
    -0.06
     Kind
    -0.06
     patrols
    -0.06
    POSITIVE LOGITS
     Interestingly
    0.07
     이전
    0.06
     Pitt
    0.06
    하다
    0.06
     pocházet
    0.06
    MJ
    0.06
    .execSQL
    0.06
    ΥΝ
    0.06
    _OPTIONS
    0.06
     зроб
    0.06
    Activations Density 0.009%

    No Known Activations