© 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. 109847
    Prev
    Next
    INDEX
    Explanations

    group

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of a specific group of people (often in the context of protected characteristics).

    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
     vient
    -0.07
    save
    -0.06
    昇
    -0.06
    Firstname
    -0.06
    ушка
    -0.06
    QualifiedName
    -0.06
    .ma
    -0.06
    _impl
    -0.06
     PCR
    -0.06
     kỹ
    -0.06
    POSITIVE LOGITS
     suce
    0.07
     dej
    0.07
     groups
    0.06
     орг
    0.06
    ptom
    0.06
     halves
    0.06
    空
    0.06
     half
    0.06
     何
    0.06
     důvod
    0.06
    Activations Density 0.024%

    No Known Activations