© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 7830
    Prev
    Next
    INDEX
    Explanations

    haha

    np_max-act · gemini-2.0-flash

    The neuron activates on informal laughter or chuckle tokens (e.g. “Haha,” “Lol”) indicating it’s detecting expressions of laughter.

    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
    usahaan
    -0.07
     importantly
    -0.06
    Kenn
    -0.06
    tenant
    -0.06
     MAIL
    -0.06
     ones
    -0.06
    PropertyDescriptor
    -0.06
    Britain
    -0.06
    .Gson
    -0.06
    <dyn
    -0.06
    POSITIVE LOGITS
    编
    0.08
    �
    0.07
    UNDER
    0.07
     stability
    0.07
     herd
    0.07
    ojis
    0.07
     sanit
    0.07
     Halo
    0.06
    .program
    0.06
     trag
    0.06
    Activations Density 0.009%

    No Known Activations