© 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. 7670
    Prev
    Next
    INDEX
    Explanations

    Names/Initials

    np_max-act · gemini-2.0-flash

    This neuron activates on personal proper names, marking tokens that are people’s first or last names.

    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
    	Il
    -0.06
    $i
    -0.06
     ske
    -0.06
     düzey
    -0.06
    )index
    -0.06
     anomal
    -0.06
     HCI
    -0.06
     pseudo
    -0.06
     호출
    -0.06
     Vz
    -0.06
    POSITIVE LOGITS
    ,《
    0.08
     beetle
    0.07
    هنگ
    0.07
     listen
    0.07
    Arch
    0.06
                 
    0.06
    junction
    0.06
    人
    0.06
    -modules
    0.06
     trữ
    0.06
    Activations Density 0.083%

    No Known Activations