© 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. 6449
    Prev
    Next
    INDEX
    Explanations

    The neuron detects words and phrases signaling a lack of ethics or morality (e.g. “amoral,” “unethical,” “immoral,” “disgusting,” “unfiltered”).

    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
    PAR
    -0.07
    COD
    -0.07
    Generate
    -0.07
    ichni
    -0.07
     mogul
    -0.06
    	router
    -0.06
    _TASK
    -0.06
    pool
    -0.06
     announc
    -0.06
     ngon
    -0.06
    POSITIVE LOGITS
    )}↵
    0.06
     getList
    0.06
    (priv
    0.06
    _fee
    0.06
    ={[↵
    0.06
    rası
    0.06
    เทศ
    0.06
    .pageSize
    0.06
     }}">{{
    0.06
    .Canvas
    0.06
    Activations Density 0.024%

    No Known Activations