© 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. 27-RESID-POST-AA
    11. 110224
    Prev
    Next
    INDEX
    Explanations

    formation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Za
    -0.06
     часа
    -0.06
     mainWindow
    -0.06
     reader
    -0.06
     odio
    -0.06
     beste
    -0.06
    _INIT
    -0.05
    	reader
    -0.05
     fundra
    -0.05
     occupancy
    -0.05
    POSITIVE LOGITS
    ..↵
    0.07
     MOV
    0.07
     �
    0.07
    aturity
    0.07
     백
    0.07
    Vari
    0.07
    Comfort
    0.07
    cü
    0.06
    othermal
    0.06
    ongo
    0.06
    Activations Density 0.003%

    No Known Activations