© 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. 7237
    Prev
    Next
    INDEX
    Explanations

    car models

    np_max-act · gemini-2.0-flash

    The neuron is triggered by numeric vehicle model designations (e.g. “3 Series,” model numbers in a car lineup).

    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
     contributed
    -0.07
    ("");↵
    -0.06
     варі
    -0.06
    ologue
    -0.06
    Comparison
    -0.06
     distinguish
    -0.06
     hintText
    -0.06
    حق
    -0.06
    的时候
    -0.06
     contributes
    -0.06
    POSITIVE LOGITS
    _atts
    0.07
    nex
    0.06
    .clientWidth
    0.06
    callbacks
    0.06
    aset
    0.06
     IData
    0.06
     NSInteger
    0.06
    .endTime
    0.06
    NTSTATUS
    0.06
     glor
    0.06
    Activations Density 0.007%

    No Known Activations