© 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. 91579
    Prev
    Next
    INDEX
    Explanations

    giving advice/instructions

    np_max-act · gemini-2.0-flash

    references to seasonal changes or advice related to personal appearances, specifically hair styling.

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

    This neuron detects the modal “should” when used to introduce recommendations or advice.

    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
     sider
    -0.07
     tracer
    -0.06
     obscure
    -0.06
     snapshots
    -0.06
     may
    -0.06
    uido
    -0.06
     �
    -0.06
    عب
    -0.06
     phạm
    -0.06
     snippet
    -0.06
    POSITIVE LOGITS
     should
    0.10
     FOREIGN
    0.07
     Prahy
    0.06
    _ct
    0.06
    lament
    0.06
    "]}↵
    0.06
    ($(".
    0.06
     Neg
    0.06
    atitis
    0.06
    _bank
    0.06
    Activations Density 0.211%

    No Known Activations