© 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. 11-RESID-POST-AA
    11. 23113
    Prev
    Next
    INDEX
    Explanations

    death

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EDIATEK
    -0.06
    ocrates
    -0.06
    stab
    -0.06
    Elem
    -0.06
    enz
    -0.06
    емых
    -0.06
     cheeks
    -0.06
    _idx
    -0.06
    189
    -0.06
    ira
    -0.06
    POSITIVE LOGITS
     κορ
    0.07
     قالب
    0.07
     …↵
    0.07
    .algorithm
    0.06
    宅
    0.06
     pry
    0.06
     inne
    0.06
     Reported
    0.06
    ?q
    0.06
     Vermont
    0.06
    Activations Density 0.031%

    No Known Activations