© 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. 128291
    Prev
    Next
    INDEX
    Explanations

    countries

    np_max-act · gemini-2.0-flash

    The neuron detects the special “assistant” header/control token marking the start of the assistant’s response.

    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
    esign
    -0.07
    Alive
    -0.07
    んど
    -0.06
    μένες
    -0.06
    Contr
    -0.06
     Giants
    -0.06
     substance
    -0.06
    immutable
    -0.06
    ured
    -0.06
     interpolate
    -0.06
    POSITIVE LOGITS
    .fecha
    0.07
     メ
    0.06
     nhà
    0.06
     Shelley
    0.06
    ντ
    0.06
    (add
    0.06
     �
    0.06
     buffet
    0.06
    .Navigate
    0.06
    operand
    0.06
    Activations Density 0.055%

    No Known Activations