© 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
    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. 91504
    Prev
    Next
    INDEX
    Explanations

    studies with people

    np_max-act · gemini-2.0-flash

    This neuron activates on terms referring to human study participants or subject groups (e.g., “patients,” “subjects,” “individuals,” “eyes,” “men”).

    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
    Für
    -0.07
     آماده
    -0.07
    _PRO
    -0.07
    Community
    -0.07
     next
    -0.06
    	sub
    -0.06
     env
    -0.06
     }))
    -0.06
    _to
    -0.06
     پرداخت
    -0.06
    POSITIVE LOGITS
    illus
    0.07
     chauff
    0.06
    -mon
    0.06
     mụn
    0.06
    영
    0.06
    idade
    0.06
    loff
    0.06
     deux
    0.06
     robert
    0.06
    ิช
    0.06
    Activations Density 0.054%

    No Known Activations