© 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 EvalsExportsinterp-engineNEWAPI 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. 58345
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns

    np_max-act · gemini-2.0-flash

    conversations that involve potentially harmful or inappropriate content.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on polite assistant offer‐to‐help or “let me know/ask me” phrases.

    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
     saints
    -0.08
     Hispanic
    -0.06
     nivel
    -0.06
    靠
    -0.06
     Fallen
    -0.06
     nhất
    -0.06
     Kap
    -0.06
    表示
    -0.06
     соз
    -0.06
     Fey
    -0.06
    POSITIVE LOGITS
    이나
    0.07
    VERTISE
    0.07
     TableColumn
    0.07
     تعمیر
    0.06
    alış
    0.06
    .Many
    0.06
     içeri
    0.06
     Revenge
    0.06
    reme
    0.06
    ้าน
    0.06
    Activations Density 0.032%

    No Known Activations