© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 85771
    Prev
    Next
    INDEX
    Explanations

    integrity

    np_max-act · gemini-2.0-flash

    The neuron activates on words conveying moral or ethical qualities (e.g. integrity, good, Karma).

    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
    ъек
    -0.07
     Pare
    -0.06
    }','
    -0.06
    _reg
    -0.06
     ScrollView
    -0.06
     Nun
    -0.06
     Fluent
    -0.06
    Allocation
    -0.06
     praises
    -0.06
     який
    -0.06
    POSITIVE LOGITS
    λό
    0.07
     pás
    0.06
                    
↵
    0.06
    COPE
    0.06
    386
    0.06
    _loc
    0.06
    /head
    0.06
    mid
    0.06
     الميلاد
    0.06
     leaning
    0.06
    Activations Density 0.030%

    No Known Activations