© 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. 8881
    Prev
    Next
    INDEX
    Explanations

    c

    np_max-act · gemini-2.0-flash

    This neuron activates on the “c” in copyright notices—i.e. the “(c)” copyright marker.

    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
    "↵
    -0.08
    shown
    -0.07
    ##↵
    -0.06
    #↵
    -0.06
     нату
    -0.06
     güvenilir
    -0.06
    (":/
    -0.06
     LET
    -0.06
     Sol
    -0.06
    idents
    -0.06
    POSITIVE LOGITS
    -tm
    0.07
    	namespace
    0.06
    .transfer
    0.06
    (k
    0.06
    Together
    0.06
    _begin
    0.06
    níci
    0.06
    _shell
    0.06
     تأ
    0.06
    (m
    0.06
    Activations Density 0.002%

    No Known Activations