© 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. 9098
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron activates on references to political or ideological entities and their opponents (e.g. mentions of the “Chinese Communist Party,” “enemies of the Second Amendment,” 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
    	from
    -0.07
    OVER
    -0.07
     ẩn
    -0.07
    ing
    -0.06
     storage
    -0.06
     much
    -0.06
     grop
    -0.06
     Middle
    -0.06
     brutally
    -0.06
     Madagascar
    -0.06
    POSITIVE LOGITS
     OCT
    0.07
     gears
    0.06
    _K
    0.06
    __(*
    0.06
     TKey
    0.06
    .heroku
    0.06
     تأ
    0.06
     XHTML
    0.06
    >{{$
    0.06
    .hm
    0.06
    Activations Density 0.039%

    No Known Activations