© 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. 11-RESID-POST-AA
    6. 42970
    Prev
    Next
    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash

    The neuron activates on phrases introducing a villainous character by title followed by a proper name.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
     assembly
    -0.07
    Pop
    -0.07
     Blues
    -0.07
    /********
    -0.07
     sek
    -0.07
     LOOP
    -0.07
    obox
    -0.06
     Surgery
    -0.06
    ulton
    -0.06
    아파트
    -0.06
    POSITIVE LOGITS
    /Observable
    0.06
    ="${
    0.06
    wel
    0.06
     привед
    0.06
     inconsistent
    0.06
    (Qt
    0.06
    .extensions
    0.06
    دمة
    0.06
    олн
    0.06
    改革
    0.06
    Activations Density 0.105%

    No Known Activations