© 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. 126229
    Prev
    Next
    INDEX
    Explanations

    school events

    np_max-act · gemini-2.0-flash

    events that involve community service or participation.

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

    The neuron fires on tokens conveying event logistics—dates, times, numbers, and other factual announcement details.

    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
     authorized
    -0.07
     accumulation
    -0.07
     зат
    -0.06
     rolling
    -0.06
    bcc
    -0.06
    cipher
    -0.06
    ya
    -0.06
     lai
    -0.06
    YRO
    -0.06
    	seq
    -0.06
    POSITIVE LOGITS
    darwin
    0.07
    subpackage
    0.07
    ?v
    0.06
     \<
    0.06
    ريقة
    0.06
    Escort
    0.06
     kannst
    0.06
     CSI
    0.06
     (${
    0.06
    Michelle
    0.06
    Activations Density 0.087%

    No Known Activations