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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 143
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of building or evaluating materials for a uranium nuclear reactor that uses xenon as a coolant.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    phrases that introduce subordinate or relative clauses adding qualifying or comparative detail to a noun or statement.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    ,最
    -0.07
    ieu
    -0.06
     рецеп
    -0.06
    Let
    -0.06
     Nose
    -0.06
    ящих
    -0.06
     relax
    -0.06
     인구
    -0.06
     patrol
    -0.06
    iggers
    -0.06
    POSITIVE LOGITS
    .addRow
    0.07
    ollapsed
    0.07
     accordance
    0.06
    _DS
    0.06
     descriptor
    0.06
     enhance
    0.06
     interv
    0.06
     $('[
    0.06
    QPushButton
    0.06
    数
    0.06
    Activations Density 0.377%

    No Known Activations