Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 27264
    Prev
    Next
    INDEX
    Explanations

    Medical studies and data

    np_max-act · gemini-2.0-flash

    medical treatment and research findings related to oncology and patient outcomes.

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

    The neuron fires most strongly on subsections and metadata headings (e.g. analysis, institute names, study arm counts) in scientific‐paper methods sections.

    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
    ensity
    -0.07
     вироб
    -0.06
    لمه
    -0.06
     ابراه
    -0.06
    ーション
    -0.06
     tk
    -0.06
     xm
    -0.06
    -li
    -0.06
     Motorola
    -0.06
    (fake
    -0.06
    POSITIVE LOGITS
    /order
    0.07
     gypsum
    0.07
     �
    0.06
     verde
    0.06
    Canvas
    0.06
    _PREFIX
    0.06
    .Array
    0.06
     gravity
    0.06
     getOrder
    0.06
    shine
    0.06
    Activations Density 0.054%

    No Known Activations