© 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. 7691
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    The neuron activates on various inflected forms of the copular “to be” (e.g. is, are/’re, being, attained).

    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
     After
    -0.06
    적으로
    -0.06
    	            
    -0.06
    	                   
    -0.06
    ुक
    -0.06
     if
    -0.06
     từ
    -0.06
     배송
    -0.06
    233
    -0.06
    Before
    -0.06
    POSITIVE LOGITS
    bew
    0.07
    icopter
    0.07
    -eng
    0.06
     sheriff
    0.06
     कन
    0.06
    navbarSupportedContent
    0.06
    _encode
    0.06
    .lang
    0.06
    _go
    0.06
    ging
    0.06
    Activations Density 0.032%

    No Known Activations