© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 27-RESID-POST-AA
    11. 113763
    Prev
    Next
    INDEX
    Explanations

    serialization

    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
     Haven
    -0.06
     JAVA
    -0.06
     BUS
    -0.06
     picnic
    -0.06
     важ
    -0.06
     CPU
    -0.06
    (help
    -0.06
    .copyWith
    -0.06
    	Block
    -0.06
     Vista
    -0.06
    POSITIVE LOGITS
    ِر
    0.09
     Ser
    0.09
    Serializer
    0.08
    esse
    0.08
    serializer
    0.07
     SER
    0.07
    -ser
    0.07
    serialized
    0.07
    sl
    0.07
    kı
    0.07
    Activations Density 0.026%

    No Known Activations