© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 58178
    Prev
    Next
    INDEX
    Explanations

    Political, social issues

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of abstract political or policy “issue” words—e.g. terms like issues, topics, controversial, sensitive—that signal discussion of contentious subjects.

    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
    Fu
    -0.06
     Cubs
    -0.06
    .buttons
    -0.06
    Subscription
    -0.06
    Tre
    -0.06
    Jam
    -0.06
    averse
    -0.06
     scheme
    -0.06
    orf
    -0.06
    $('
    -0.06
    POSITIVE LOGITS
     mote
    0.07
    =settings
    0.07
     appellate
    0.06
    -parser
    0.06
    Override
    0.06
    regulated
    0.06
    �i
    0.06
    cli
    0.06
    .amazonaws
    0.06
    -refresh
    0.06
    Activations Density 0.048%

    No Known Activations