© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 89622
    Prev
    Next
    INDEX
    Explanations

    does

    np_max-act · gemini-2.0-flash

    The neuron is primarily triggered by the field‐label phrase “Climate type:” in the output.

    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
     Biggest
    -0.07
     (${
    -0.06
     despite
    -0.06
    .getOwnPropertyDescriptor
    -0.06
     filmes
    -0.06
    Material
    -0.06
     thicker
    -0.06
    'all
    -0.06
     spoilers
    -0.06
    (TimeSpan
    -0.06
    POSITIVE LOGITS
    arty
    0.06
     Cah
    0.06
    OPS
    0.06
    coder
    0.05
    �
    0.05
    .getInstance
    0.05
     제
    0.05
    _slot
    0.05
    .getNext
    0.05
     قي
    0.05
    Activations Density 0.003%

    No Known Activations