© 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
    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. 9093
    Prev
    Next
    INDEX
    Explanations

    republican party

    np_max-act · gemini-2.0-flash

    The neuron activates on references to formal political organization names and titles (e.g. “Republican Committee,” “National Committee,” “Party,” “Chairman,” 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
     ignorance
    -0.07
     decorate
    -0.07
    	Collection
    -0.07
    afe
    -0.06
    .parseInt
    -0.06
    πό
    -0.06
    		
↵
    -0.06
     repercussions
    -0.06
    ाष
    -0.06
    bcrypt
    -0.06
    POSITIVE LOGITS
     decl
    0.07
    icipant
    0.06
     inv
    0.06
     MISSING
    0.06
    �
    0.06
    äsent
    0.06
     CREATE
    0.06
    apanese
    0.06
    steam
    0.06
    청
    0.06
    Activations Density 0.012%

    No Known Activations