© 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. 79692
    Prev
    Next
    INDEX
    Explanations

    talk

    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_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
    theros
    -0.08
    (loop
    -0.07
    наслідок
    -0.07
     micron
    -0.06
     employs
    -0.06
     احتم
    -0.06
     سید
    -0.06
    BLOCK
    -0.06
    	output
    -0.06
     show
    -0.06
    POSITIVE LOGITS
     talk
    0.09
     talking
    0.09
     talked
    0.08
     얘
    0.08
     speak
    0.08
     discussing
    0.07
    너
    0.07
     speaking
    0.07
    语
    0.07
    enus
    0.07
    Activations Density 0.052%

    No Known Activations