© 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. 91626
    Prev
    Next
    INDEX
    Explanations

    technical discussions

    np_max-act · gemini-2.0-flash

    This neuron detects parenthetical aside comments or clarifying asides (e.g. “(If you’re reading this… )” or “(But release of a mouse button…)”).

    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
     трохи
    -0.07
     denně
    -0.07
     chỉnh
    -0.06
    	glColor
    -0.06
    Eq
    -0.06
     prostřednictvím
    -0.06
    /Core
    -0.06
     форме
    -0.06
    िशत
    -0.06
     όπως
    -0.06
    POSITIVE LOGITS
    **↵
    0.07
                
    0.06
    bo
    0.06
    .alibaba
    0.06
    ize
    0.06
     +
    ↵
    0.06
                 
    0.06
    decrypt
    0.06
     villa
    0.06
    ********************************
    0.06
    Activations Density 0.162%

    No Known Activations