© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 54162
    Prev
    Next
    INDEX
    Explanations

    Proper nouns

    np_max-act · gemini-2.0-flash

    This neuron responds to occurrences of personal names (proper names of individuals).

    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
    _dims
    -0.06
     tento
    -0.06
    228
    -0.06
    	contentPane
    -0.06
    izens
    -0.06
     thuê
    -0.06
     chac
    -0.06
     institutes
    -0.06
    _LOAD
    -0.06
     Cascade
    -0.06
    POSITIVE LOGITS
    لوب
    0.07
     الحرب
    0.06
     الموس
    0.06
    完成
    0.06
    腹
    0.06
     prohibits
    0.06
     Vienna
    0.06
     "!
    0.06
     BOOL
    0.06
    -comment
    0.06
    Activations Density 0.321%

    No Known Activations