© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 42574
    Prev
    Next
    INDEX
    Explanations

    add

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect programming action verbs that add or append data (e.g. “add,” “append,” “write”).

    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
    44
    -0.06
     spotting
    -0.06
     presenter
    -0.06
     charging
    -0.06
    Develop
    -0.06
     PW
    -0.06
     veggies
    -0.06
     critique
    -0.06
     narrowing
    -0.06
    بدأ
    -0.06
    POSITIVE LOGITS
     geg
    0.07
    indeki
    0.07
    ‌کن
    0.07
    .fillStyle
    0.06
    ầm
    0.06
    Selector
    0.06
    ADED
    0.06
    存
    0.06
     Weapon
    0.06
    --){↵
    0.06
    Activations Density 0.025%

    No Known Activations