© 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. 68572
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    This neuron activates on code patterns that set or assign object properties—specifically on `dataset.set…` (and similar) method calls and ensuing property‐assignment tokens.

    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
    gether
    -0.07
     hoax
    -0.07
     Youtube
    -0.06
     життя
    -0.06
    出す
    -0.06
     Budapest
    -0.06
     Sund
    -0.06
     shipping
    -0.06
    few
    -0.06
     нагруз
    -0.06
    POSITIVE LOGITS
    Alice
    0.06
    ))/(
    0.06
    prm
    0.06
    erek
    0.06
    ')}>↵
    0.06
     NDP
    0.06
     tactic
    0.06
    .getVersion
    0.06
    ulated
    0.06
    Emoji
    0.06
    Activations Density 0.018%

    No Known Activations