© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 129778
    Prev
    Next
    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash

    The neuron detects words that are part of hyperlink anchor text or link labels in HTML or wiki markup.

    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
     Surg
    -0.07
     않았다
    -0.07
     folding
    -0.07
    ắt
    -0.07
    ंत
    -0.06
    crement
    -0.06
     ممن
    -0.06
     Legendary
    -0.06
     puppy
    -0.06
     hug
    -0.06
    POSITIVE LOGITS
     Extras
    0.07
    >)
    0.06
    	glut
    0.06
    )
    
    ↵
    0.06
     Crusher
    0.06
    /]
    0.06
    _EVAL
    0.06
     تكون
    0.06
     mín
    0.06
     omitted
    0.06
    Activations Density 0.006%

    No Known Activations