© 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. 126040
    Prev
    Next
    INDEX
    Explanations

    Drug control

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect terms related to the illegality or legal regulation of activities (e.g., “illegal,” “regulated,” “distribution”).

    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
     merged
    -0.07
    Numer
    -0.06
     �
    -0.06
    half
    -0.06
    go
    -0.06
     scept
    -0.06
    career
    -0.06
    _age
    -0.06
    ãi
    -0.06
    rary
    -0.06
    POSITIVE LOGITS
     dela
    0.07
     исследования
    0.07
     prosecutions
    0.07
     العامة
    0.07
     warto
    0.07
    ({↵↵
    0.06
     court
    0.06
     require
    0.06
     زنی
    0.06
     controversial
    0.06
    Activations Density 0.015%

    No Known Activations