© 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. 3-RESID-POST-AA
    11. 123132
    Prev
    Next
    INDEX
    Explanations

    immigrant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     нашей
    -0.07
     foresee
    -0.06
     rece
    -0.06
     supplementary
    -0.06
    Fax
    -0.06
     каб
    -0.06
    facebook
    -0.06
    issing
    -0.06
    ları
    -0.06
     casting
    -0.06
    POSITIVE LOGITS
     immigrant
    0.26
     immigrants
    0.26
    igrants
    0.21
    igrant
    0.19
     migrant
    0.19
     migrants
    0.17
     seventy
    0.08
    _DECLS
    0.07
     Herman
    0.06
    -parent
    0.06
    Activations Density 0.002%

    No Known Activations