© 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. 110120
    Prev
    Next
    INDEX
    Explanations

    actions, doing things

    np_max-act · gemini-2.0-flash

    phrases related to manipulation and deceitful practices.

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

    This neuron activates on instances of the preposition “in” introducing a manner phrase—especially “in … way(s)” or “in … particular” constructions.

    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
     indirect
    -0.06
     เต
    -0.06
    ождения
    -0.06
    ={`${
    -0.06
    нім
    -0.06
     excl
    -0.06
    }_${
    -0.06
    RSA
    -0.06
    Wir
    -0.06
    .uri
    -0.06
    POSITIVE LOGITS
     pys
    0.06
     شهرد
    0.06
    สด
    0.06
     look
    0.06
    .asp
    0.06
     풍
    0.06
     Fixture
    0.06
     MOV
    0.06
     saga
    0.06
     Jake
    0.05
    Activations Density 0.051%

    No Known Activations