© 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. 19-RESID-POST-AA
    11. 111655
    Prev
    Next
    INDEX
    Explanations

    execute

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    292
    -0.06
     parler
    -0.06
     pilot
    -0.06
    اطعة
    -0.06
    .........
    -0.06
    _SOCKET
    -0.06
    Db
    -0.06
     COOKIE
    -0.05
    	num
    -0.05
     vie
    -0.05
    POSITIVE LOGITS
    lanma
    0.08
     UA
    0.07
     Δι
    0.07
     Львів
    0.06
    itet
    0.06
     çalışan
    0.06
    orget
    0.06
     permanent
    0.06
    ório
    0.06
    mî
    0.06
    Activations Density 0.035%

    No Known Activations