© 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
    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. 74787
    Prev
    Next
    INDEX
    Explanations

    Defining a process

    np_max-act · gemini-2.0-flash

    This neuron activates on definition-style phrases—tokens like “refers to,” “is the process of,” or “meaning” that introduce or signal a definition.

    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
    growth
    -0.07
     Pandora
    -0.06
    xiety
    -0.06
    Photon
    -0.06
    Safety
    -0.06
    지원
    -0.06
    ator
    -0.06
     dispro
    -0.06
     信
    -0.05
     economics
    -0.05
    POSITIVE LOGITS
    oves
    0.07
    /gr
    0.07
    IRTUAL
    0.07
     verilm
    0.07
    FROM
    0.07
    enses
    0.07
    undra
    0.07
    .columnHeader
    0.07
     zahrn
    0.06
     nejlepší
    0.06
    Activations Density 0.087%

    No Known Activations