© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 128651
    Prev
    Next
    INDEX
    Explanations

    u

    np_max-act · gemini-2.0-flash

    Jewish religious terminology and names, particularly Hebrew words transliterated into English.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @andyrdt
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anybody
    -0.07
    효
    -0.06
    jure
    -0.06
     anyone
    -0.06
     ce
    -0.06
    ë
    -0.06
    	import
    -0.05
     공간
    -0.05
     questo
    -0.05
     united
    -0.05
    POSITIVE LOGITS
    itizer
    0.07
     Mp
    0.07
     Veterans
    0.07
                     
    0.07
     iVar
    0.06
    retorno
    0.06
    ровер
    0.06
    .LAZY
    0.06
    شماری
    0.06
    �
    0.06
    Activations Density 0.023%

    No Known Activations