© 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. 7-RESID-POST-AA
    11. 120899
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    legal case metadata in judicial opinions, including reporter citations, court/case headings, parties, and decision/argument dates.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ố
    -0.07
    尘
    -0.06
    _tweets
    -0.06
    amples
    -0.06
    ards
    -0.06
    	stack
    -0.06
    禮
    -0.06
     pinch
    -0.06
     Dud
    -0.06
    悪
    -0.06
    POSITIVE LOGITS
     Implements
    0.07
     člověk
    0.07
     práva
    0.07
     enhances
    0.07
     TableName
    0.06
     dzie
    0.06
     παρα
    0.06
    lov
    0.06
     bee
    0.06
     بول
    0.06
    Activations Density 0.047%

    No Known Activations