© 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. 7571
    Prev
    Next
    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “name,” flagging passages where something’s name is being given or defined.

    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
    trys
    -0.07
    .jsp
    -0.07
    Watching
    -0.07
     stos
    -0.06
    -induced
    -0.06
    ected
    -0.06
     Kubernetes
    -0.06
    oured
    -0.06
     chaos
    -0.06
    ève
    -0.06
    POSITIVE LOGITS
     FormsModule
    0.07
     dei
    0.06
     Joh
    0.06
     mods
    0.06
    =?
    0.06
     conception
    0.06
     göç
    0.06
     topLevel
    0.06
     πλη
    0.06
    /footer
    0.06
    Activations Density 0.009%

    No Known Activations