© 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. 925
    Prev
    Next
    INDEX
    Explanations

    economic

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of the core economic domain—tokens like “economic,” “economy,” or closely related forms.

    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
    ilerek
    -0.07
    .softmax
    -0.07
     потрап
    -0.06
     bathrooms
    -0.06
    _soft
    -0.06
    .setColumns
    -0.06
     Анг
    -0.06
    ("//*[@
    -0.06
    잡
    -0.06
    .isNotBlank
    -0.06
    POSITIVE LOGITS
     cứu
    0.08
     polling
    0.06
    ');?>↵
    0.06
    ुन
    0.06
    ethical
    0.06
    oundation
    0.06
    سر
    0.06
    =com
    0.06
    Ν
    0.06
    [S
    0.06
    Activations Density 0.005%

    No Known Activations