© 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. 4713
    Prev
    Next
    INDEX
    Explanations

    to

    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
     binge
    -0.06
    	socket
    -0.06
    ｱ
    -0.06
    classpath
    -0.06
    .getUserName
    -0.06
    "use
    -0.06
    体
    -0.06
     thuyết
    -0.06
     现
    -0.06
     getKey
    -0.06
    POSITIVE LOGITS
     bribery
    0.06
     Partisi
    0.06
     exerc
    0.06
    寸
    0.06
     Candid
    0.06
     спис
    0.06
     frees
    0.05
     obed
    0.05
     LOAD
    0.05
    36
    0.05
    Activations Density 0.116%

    No Known Activations