© 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. 29787
    Prev
    Next
    INDEX
    Explanations

    support

    np_max-act · gemini-2.0-flash

    The neuron consistently activates on tokens from the assistant’s generated responses (and stays silent on user input), effectively marking “assistant-side” text.

    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
     Omni
    -0.06
     배송
    -0.06
    _evt
    -0.06
    $password
    -0.06
     شرح
    -0.06
     ниже
    -0.06
    >Error
    -0.06
     المح
    -0.06
     因
    -0.06
     blanks
    -0.06
    POSITIVE LOGITS
    BR
    0.06
    طفال
    0.06
    lus
    0.06
     Elle
    0.06
    .Tool
    0.06
    ленные
    0.06
    Tool
    0.06
    .seq
    0.06
     outs
    0.06
    atasets
    0.06
    Activations Density 0.042%

    No Known Activations