© 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. 126739
    Prev
    Next
    INDEX
    Explanations

    First person plural

    np_max-act · gemini-2.0-flash

    discussions about societal roles and expectations related to women and gender.

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

    This neuron responds to first‐person plural pronouns (we, us).

    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
    torch
    -0.07
     flowers
    -0.06
     lexer
    -0.06
    VERN
    -0.06
     осіб
    -0.06
     بلند
    -0.06
    .Se
    -0.06
    ве
    -0.06
    papers
    -0.06
    LOB
    -0.06
    POSITIVE LOGITS
     skvěl
    0.06
     неск
    0.06
     pinned
    0.06
    !";↵
    0.06
    0.06
    ';
↵
    0.06
    	  ↵
    0.06
     wreak
    0.06
    sw
    0.06
     leží
    0.06
    Activations Density 0.046%

    No Known Activations