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. 55266
    Prev
    Next
    INDEX
    Explanations

    duction

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect mentions of “conduction,” especially in the context of cardiac conduction or conduction abnormalities.

    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
    ,Integer
    -0.08
     Ром
    -0.07
    _saida
    -0.07
    xce
    -0.06
    ynamodb
    -0.06
     розрах
    -0.06
     trong
    -0.06
     karşılaş
    -0.06
     claw
    -0.06
    ,LOCATION
    -0.06
    POSITIVE LOGITS
     blockers
    0.07
     binding
    0.07
    ussian
    0.06
    ��态
    0.06
    AGENT
    0.06
    829
    0.06
    -gap
    0.06
    _DIST
    0.06
     rate
    0.06
     homeland
    0.06
    Activations Density 0.001%

    No Known Activations