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

    Neuronpedia

    Jacobian LensNEW
    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. 56507
    Prev
    Next
    INDEX
    Explanations

    journal publications

    np_max-act · gemini-2.0-flash

    topics related to scientific studies on environmental and biological impacts.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron is triggered by numeric year tokens (publication dates) in reference citations.

    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
    urrenc
    -0.07
     HMAC
    -0.07
    وقيت
    -0.07
    .NAME
    -0.06
    (vertex
    -0.06
    수가
    -0.06
    orianCalendar
    -0.06
    /tmp
    -0.06
    živ
    -0.06
    PRS
    -0.06
    POSITIVE LOGITS
     [],↵
    0.07
     Rotterdam
    0.06
     Scripture
    0.06
     claimed
    0.06
    雷
    0.06
    τερ
    0.06
    梅
    0.06
     فإن
    0.06
     vanity
    0.06
     función
    0.06
    Activations Density 0.005%

    No Known Activations