© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 20544
    Prev
    Next
    INDEX
    Explanations

    conversational text

    np_max-act · gemini-2.0-flash

    the neuron fires on utterances that express agreement/acknowledgement or apologies directed at the user (e.g., "You are right", "I apologize", "I understand").

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    níku
    -0.07
     буде
    -0.07
    хов
    -0.07
    gr
    -0.06
    HEL
    -0.06
     Juli
    -0.06
    lahoma
    -0.06
     зави
    -0.06
    �
    -0.06
     coraz
    -0.06
    POSITIVE LOGITS
     marc
    0.08
     marque
    0.07
    Thank
    0.07
    および
    0.06
    }↵
    0.06
     mortal
    0.06
    ,↵
    0.06
     framerate
    0.06
    Struct
    0.06
    	Label
    0.06
    Activations Density 0.065%

    No Known Activations