© 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. 714
    Prev
    Next
    INDEX
    Explanations

    forum posts

    np_max-act · gemini-2.0-flash

    the neuron is detecting first-person self-references, especially the pronoun “I.”

    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
    ↵
↵
↵
↵
    -0.06
     Cron
    -0.06
     language
    -0.06
     Accent
    -0.06
     sno
    -0.06
    (userId
    -0.06
     lore
    -0.06
    StartPosition
    -0.06
    цями
    -0.05
    _read
    -0.05
    POSITIVE LOGITS
    ivet
    0.07
    Goals
    0.06
     odbor
    0.06
    imiter
    0.06
     competit
    0.06
     �
    0.06
    stub
    0.06
    /es
    0.06
    ﺘ
    0.06
     chiff
    0.06
    Activations Density 0.142%

    No Known Activations