© 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. 6568
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    This neuron detects the standard lead‐in phrases of French Wikipedia articles about communes (e.g. “<Name> is a commune in the <Department> department in <Region> France”).

    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
     зали
    -0.07
     Germ
    -0.07
     Kerr
    -0.06
     مست
    -0.06
    .cwd
    -0.06
    ยน
    -0.06
     spr
    -0.06
    +m
    -0.06
     ラ
    -0.06
     Console
    -0.06
    POSITIVE LOGITS
     پوست
    0.07
     Apollo
    0.07
    ]:=
    0.06
    وزی
    0.06
     violating
    0.06
     yasal
    0.06
     Constructs
    0.06
    cdc
    0.06
     vero
    0.06
    ificance
    0.06
    Activations Density 0.017%

    No Known Activations