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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 128428
    Prev
    Next
    INDEX
    Explanations

    imaging, automation, writing

    np_max-act · gemini-2.0-flash

    The neuron is primarily detecting occurrences of the phrase “image recognition.”

    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
    ávací
    -0.06
    ////////////////////////////////////////////////////////////////////////
    -0.06
    IGH
    -0.06
    едь
    -0.06
    wayne
    -0.06
    出现
    -0.06
     وجود
    -0.06
    енным
    -0.06
    pler
    -0.06
    iode
    -0.05
    POSITIVE LOGITS
     decking
    0.07
    [frame
    0.07
    	Image
    0.07
    eming
    0.07
    σμού
    0.07
    /left
    0.07
    (()=>{↵
    0.07
    *)&
    0.06
     rtn
    0.06
    )./
    0.06
    Activations Density 0.259%

    No Known Activations