© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30103
    Prev
    Next
    INDEX
    Explanations

    fell

    np_max-act · gemini-2.0-flash

    The neuron responds to words and phrases that signal economic or monetary details—especially references to financial changes, salaries, benefits, and expenditures.

    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
    iz
    -0.07
    ae
    -0.07
     ALPHA
    -0.06
     Marty
    -0.06
    jerne
    -0.06
    ap
    -0.06
     Grant
    -0.06
     America
    -0.06
    guided
    -0.06
    rase
    -0.06
    POSITIVE LOGITS
    .DateTimeField
    0.08
    ->{
    0.07
    <translation
    0.07
    ">'+
    0.07
    /sites
    0.07
    ľ
    0.06
    .vertical
    0.06
    _alignment
    0.06
    .DateField
    0.06
    --
↵
    0.06
    Activations Density 0.209%

    No Known Activations