© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 55886
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron specifically picks up the capitalized “To” as it appears in the “Subscribe To” header element.

    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
    .magic
    -0.07
    clubs
    -0.07
    Fort
    -0.07
     معت
    -0.07
    igma
    -0.07
    fik
    -0.07
    (remove
    -0.06
    им
    -0.06
    >↵↵
    -0.06
     수상
    -0.06
    POSITIVE LOGITS
    출장마사지
    0.07
    swagen
    0.07
     uppercase
    0.06
    									 
    0.06
     orth
    0.06
     ilgili
    0.06
    ικές
    0.06
    illez
    0.06
     phương
    0.06
    аліст
    0.06
    Activations Density 0.008%

    No Known Activations