© 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. 66127
    Prev
    Next
    INDEX
    Explanations

    Apologies and responsibility

    np_max-act · gemini-2.0-flash

    The neuron activates on apology-language—words and phrases expressing regret or taking responsibility (e.g. “acknowledge your part,” “sorry,” “regret,” “make amends”).

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

    phrases related to acknowledging mistakes and taking responsibility.

    oai_token-act-pair · gpt-4o-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
     Unidos
    -0.07
     пацієн
    -0.07
     بود
    -0.07
     сразу
    -0.06
    宏
    -0.06
    نان
    -0.06
     resultant
    -0.06
     delays
    -0.06
     オ
    -0.06
    41
    -0.06
    POSITIVE LOGITS
    CNN
    0.07
    %d
    0.07
     earning
    0.07
     vrouw
    0.07
     موقعیت
    0.07
    mentor
    0.06
     {!!
    0.06
    .column
    0.06
     Carrier
    0.06
    .squeeze
    0.06
    Activations Density 0.079%

    No Known Activations