© 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. 126789
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on named entities and other specific technical or proper nouns (e.g. organization names, people’s names, specialized terms).

    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
     Tik
    -0.07
     Fernando
    -0.06
     Heritage
    -0.06
    FK
    -0.06
    ela
    -0.06
     TODAY
    -0.06
     Paul
    -0.06
     appealing
    -0.06
    .one
    -0.06
     دانشگاه
    -0.06
    POSITIVE LOGITS
    اختی
    0.07
    	JOptionPane
    0.07
     اختصاص
    0.07
    Ros
    0.07
    Trad
    0.07
    propri
    0.06
    Happy
    0.06
    creates
    0.06
     imperson
    0.06
        
    0.06
    Activations Density 0.180%

    No Known Activations