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

    Neuronpedia

    Jacobian LensNEW
    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. 38308
    Prev
    Next
    INDEX
    Explanations

    Lies and deception

    np_max-act · gemini-2.0-flash

    The neuron fires on proper names and other salient content words—especially film titles, character names, and key plot–driving terms—in movie descriptions.

    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
    bp
    -0.06
     Kur
    -0.06
     pest
    -0.06
    Fetch
    -0.06
    ymes
    -0.06
    ้ก
    -0.06
    вався
    -0.06
    -values
    -0.06
     stones
    -0.06
     đãi
    -0.06
    POSITIVE LOGITS
     fis
    0.07
    .Errorf
    0.07
    ическая
    0.07
    hashed
    0.07
    +n
    0.07
    mage
    0.06
    !")↵↵
    0.06
     принадлеж
    0.06
    .NumericUpDown
    0.06
     POS
    0.06
    Activations Density 0.072%

    No Known Activations