Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 528
    Prev
    Next
    INDEX
    Explanations

    Reopening

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of services or venues being reopened or resuming operation after a disruption.

    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
    _complete
    -0.07
     eg
    -0.07
     OK
    -0.07
     OH
    -0.06
    .K
    -0.06
     Naw
    -0.06
     цвет
    -0.06
    .obj
    -0.06
     tuple
    -0.06
     земля
    -0.06
    POSITIVE LOGITS
     northern
    0.07
     particularly
    0.07
     envelope
    0.06
     tamamen
    0.06
    なし
    0.06
     shrimp
    0.06
     necesario
    0.06
     ağ
    0.06
    ύ
    0.06
    Juan
    0.06
    Activations Density 0.009%

    No Known Activations