© 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. 44471
    Prev
    Next
    INDEX
    Explanations

    maximize

    np_max-act · gemini-2.0-flash

    text related to algorithms and methods in reinforcement learning.

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

    This neuron detects occurrences of “maximize” (and its variants) indicating an optimization objective in the text.

    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
    /p
    -0.06
    ’app
    -0.06
     towards
    -0.06
     مخصوص
    -0.06
    Dict
    -0.06
    .check
    -0.06
    pton
    -0.06
    路径
    -0.06
     Sans
    -0.05
    (dw
    -0.05
    POSITIVE LOGITS
    чик
    0.07
     HomeController
    0.07
    dc
    0.07
     elevate
    0.06
    zend
    0.06
    —as
    0.06
     boto
    0.06
    olicy
    0.06
     Creative
    0.06
    supplier
    0.06
    Activations Density 0.012%

    No Known Activations