© 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. 41583
    Prev
    Next
    INDEX
    Explanations

    set

    np_max-act · gemini-2.0-flash

    code related to the structure and functionality of a software library.

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

    The neuron fires on occurrences of method names starting with “set” (i.e. setter method definitions).

    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
    进一步
    -0.06
    hm
    -0.06
    .Optional
    -0.06
     �
    -0.06
     Retrieves
    -0.06
    jected
    -0.06
    verting
    -0.06
    Windows
    -0.06
    Question
    -0.06
     vocabulary
    -0.06
    POSITIVE LOGITS
    ednou
    0.08
    searchModel
    0.07
     náp
    0.07
    HasBeenSet
    0.07
     jednodu
    0.06
     اروپ
    0.06
     UIPickerView
    0.06
     찾아
    0.06
     KeyValuePair
    0.06
     προς
    0.06
    Activations Density 0.008%

    No Known Activations