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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 126201
    Prev
    Next
    INDEX
    Explanations

    News/Politics

    np_max-act · gemini-2.0-flash

    The neuron flags mentions of U.S. political institutions and offices (e.g. “United States Senate,” “CIA Chief,” “political correspondent”).

    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
     iterations
    -0.06
    _chr
    -0.06
     inversion
    -0.06
     Skills
    -0.06
    interest
    -0.06
    칭
    -0.06
     customer
    -0.06
     motivate
    -0.06
    CHAN
    -0.06
     pubs
    -0.06
    POSITIVE LOGITS
    ////////////////////////////////////////////////////////////////////////////////////////////////
    0.07
     Dice
    0.07
     OnClickListener
    0.07
     můj
    0.07
    unger
    0.07
     sécur
    0.07
     dnes
    0.06
     onPostExecute
    0.06
    Ng
    0.06
    ejména
    0.06
    Activations Density 0.038%

    No Known Activations