© 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. 90975
    Prev
    Next
    INDEX
    Explanations

    code/technical descriptions

    np_max-act · gemini-2.0-flash

    This neuron identifies JSON or instruction field keywords—particularly terms like “verbatim,” “need,” “category,” and “satisfaction.”

    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
     ブ
    -0.07
     Item
    -0.07
    ############################################################
    -0.07
    出す
    -0.06
    MapView
    -0.06
     aValue
    -0.06
    れる
    -0.06
    Benef
    -0.06
    .AF
    -0.06
    主義
    -0.06
    POSITIVE LOGITS
    ('/')[-
    0.06
     Респ
    0.06
    ")){↵
    0.06
    .'</
    0.06
    اتی
    0.06
    [cnt
    0.06
    а�
    0.06
     cq
    0.06
     erfolgreich
    0.06
    quit
    0.06
    Activations Density 0.023%

    No Known Activations