© 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. 7-RESID-POST-AA
    11. 75822
    Prev
    Next
    INDEX
    Explanations

    causing

    np_max-act · gemini-2.0-flash
    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
    ,but
    -0.06
    ldr
    -0.06
    ,and
    -0.06
     spooky
    -0.06
    ่วน
    -0.06
     Bitcoins
    -0.06
    ć
    -0.06
    러운
    -0.06
    card
    -0.06
    ۷
    -0.06
    POSITIVE LOGITS
     meddling
    0.07
    	trigger
    0.07
    lightbox
    0.06
    	mode
    0.06
     militants
    0.06
    rıca
    0.06
    .swift
    0.06
     кроме
    0.06
    ,
    0.06
     строк
    0.06
    Activations Density 1.315%

    No Known Activations