© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 128631
    Prev
    Next
    INDEX
    Explanations

    data types

    np_max-act · gemini-2.0-flash

    This neuron responds to numerical tokens—especially score values and other digits in the JSON‐style responses.

    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
     HOL
    -0.06
    .Car
    -0.06
     جهان
    -0.06
    (pd
    -0.06
     millenn
    -0.06
    _IT
    -0.06
    .getDocument
    -0.06
    ソン
    -0.06
     Роз
    -0.06
     XC
    -0.06
    POSITIVE LOGITS
     ignoring
    0.07
    =settings
    0.07
     jun
    0.06
     sitting
    0.06
    说话
    0.06
    vari
    0.06
    locale
    0.06
    wives
    0.06
    uid
    0.06
     треб
    0.06
    Activations Density 0.002%

    No Known Activations