© 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. 29605
    Prev
    Next
    INDEX
    Explanations

    Code syntax

    np_max-act · gemini-2.0-flash

    This neuron activates on CamelCase type or class names (i.e. multi-word identifiers like SingleServiceTracker, ForegroundHelper, Flags, MetadataLookup, BuildParams, etc.).

    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
    Intel
    -0.08
    _py
    -0.07
    /DD
    -0.07
    Distance
    -0.07
    EA
    -0.07
     thinks
    -0.07
     working
    -0.07
    حق
    -0.07
    enn
    -0.07
    STA
    -0.07
    POSITIVE LOGITS
     Calls
    0.06
    .scalar
    0.06
     NotImplementedException
    0.06
     рабо
    0.06
     spiked
    0.06
     HTMLElement
    0.06
     Lagos
    0.06
    lectic
    0.06
    selectorMethod
    0.06
     CGPoint
    0.05
    Activations Density 0.019%

    No Known Activations