© 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. 91618
    Prev
    Next
    INDEX
    Explanations

    interest

    np_max-act · gemini-2.0-flash

    The neuron detects legal terms and phrases referring to constitutional “liberty” or “property” interests—especially in the context of due process clauses.

    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
     chooses
    -0.07
     jet
    -0.07
    _tls
    -0.07
     operational
    -0.06
     pounded
    -0.06
     Unit
    -0.06
    _properties
    -0.06
     printing
    -0.06
     server
    -0.06
     gần
    -0.06
    POSITIVE LOGITS
     우리
    0.07
    [image
    0.07
     physicists
    0.07
     InvalidOperationException
    0.06
     TextStyle
    0.06
     Scandin
    0.06
     bitk
    0.06
    */),
    0.06
    잡담
    0.06
    =subprocess
    0.06
    Activations Density 0.002%

    No Known Activations