© 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. 54148
    Prev
    Next
    INDEX
    Explanations

    retroactive

    np_max-act · gemini-2.0-flash

    the neuron's main function is to detect references to retroactive timing or backdating (terms like “retroactive,” “backdate,” or “predate”).

    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
    entanyl
    -0.07
    elve
    -0.07
     Chiefs
    -0.07
     Rising
    -0.06
     Leon
    -0.06
     lows
    -0.06
    signal
    -0.06
    神
    -0.06
    圭圭
    -0.06
    -one
    -0.06
    POSITIVE LOGITS
    GetMethod
    0.08
     규
    0.07
    -compatible
    0.07
     المدينة
    0.07
    ifies
    0.06
     защ
    0.06
     Joh
    0.06
    níci
    0.06
     دولار
    0.06
    ↵      ↵
    0.06
    Activations Density 0.004%

    No Known Activations