© 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. 54058
    Prev
    Next
    INDEX
    Explanations

    surf

    np_max-act · gemini-2.0-flash

    The neuron flags computer/Internet–related jargon, especially words about digital data handling (e.g. surf, cache, streaming, drive, data warehouses, widgets).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    topics related to politics and public figures.

    oai_token-act-pair · gpt-4o-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
     head
    -0.07
    _rent
    -0.07
    operate
    -0.07
     Shopify
    -0.07
     faster
    -0.07
     žen
    -0.06
     เร
    -0.06
    _finish
    -0.06
     Gordon
    -0.06
     tốt
    -0.06
    POSITIVE LOGITS
    mar
    0.08
     чин
    0.07
    bic
    0.06
    (Collections
    0.06
     Indi
    0.06
     حکومت
    0.06
    507
    0.06
     zároveň
    0.06
    (\'
    0.06
    $array
    0.06
    Activations Density 0.202%

    No Known Activations