© 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. 124894
    Prev
    Next
    INDEX
    Explanations

    Drugs and incarceration

    np_max-act · gemini-2.0-flash

    The neuron fires on terms related to criminal justice and incarceration, especially around drug enforcement and arrest statistics.

    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
    .activity
    -0.07
    .imgur
    -0.07
    ów
    -0.07
     Development
    -0.07
    _reduction
    -0.07
    _completion
    -0.07
     {*}
    -0.06
     Boulevard
    -0.06
    開発
    -0.06
    			       
    -0.06
    POSITIVE LOGITS
    ichick
    0.07
    ῶν
    0.06
    ag
    0.06
    .imageView
    0.05
    مول
    0.05
     رئيس
    0.05
     bailout
    0.05
     بسي
    0.05
    ูม
    0.05
     γε
    0.05
    Activations Density 0.005%

    No Known Activations