© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 125250
    Prev
    Next
    INDEX
    Explanations

    political coalitions

    np_max-act · gemini-2.0-flash

    The neuron fires on terms relating to the formation of coalition or minority governments (e.g. “forming,” “coalition,” “minority,” “administration,” “support”).

    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
     Benefit
    -0.07
     канди
    -0.07
    -0.07
     uydu
    -0.07
    	doc
    -0.06
     роки
    -0.06
     doch
    -0.06
     Preferences
    -0.06
     ainda
    -0.06
    nea
    -0.06
    POSITIVE LOGITS
    zzle
    0.06
    locs
    0.06
     Politics
    0.06
    osomes
    0.06
     Gina
    0.06
    _LEG
    0.06
     printed
    0.06
     gutter
    0.06
     iam
    0.06
     جامعة
    0.06
    Activations Density 0.014%

    No Known Activations