© 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. 85706
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron fires on words indicating “self” or “internal” (e.g. self-, próprias, internamente) to spot mentions of something being done in-house or by one’s own entity.

    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
     shark
    -0.08
     (@
    -0.07
     Gupta
    -0.07
     Upon
    -0.07
    (${
    -0.06
     books
    -0.06
     Alicia
    -0.06
     brought
    -0.06
    .cfg
    -0.06
    "g
    -0.06
    POSITIVE LOGITS
    ğı
    0.07
     �
    0.06
    jj
    0.06
    imshow
    0.06
     příprav
    0.06
    äl
    0.06
    STRUCTOR
    0.06
    StrLn
    0.06
     setattr
    0.06
    DevExpress
    0.06
    Activations Density 0.245%

    No Known Activations