© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 41584
    Prev
    Next
    INDEX
    Explanations

    shapes

    np_max-act · gemini-2.0-flash

    This neuron activates on words describing geometric shapes or shape-related descriptors (e.g. “shape,” “oval,” “elliptical,” “nonspherical,” etc.).

    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
    Bean
    -0.06
    .Models
    -0.06
    (Transaction
    -0.06
    -light
    -0.06
    .Ent
    -0.06
    UserData
    -0.06
    för
    -0.06
    едагог
    -0.06
    (z
    -0.06
    _VLAN
    -0.06
    POSITIVE LOGITS
    �
    0.07
    metis
    0.06
     �
    0.06
     برنامه
    0.06
     deprivation
    0.06
     張
    0.06
    抬
    0.06
    ียนร
    0.06
     الأسر
    0.06
     Alloc
    0.06
    Activations Density 0.099%

    No Known Activations