© 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. 90808
    Prev
    Next
    INDEX
    Explanations

    adversarial

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of “adversarial” or “GAN,” i.e. references to Generative Adversarial Networks.

    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
     OK
    -0.07
    _on
    -0.07
     pollution
    -0.07
    -day
    -0.07
    uos
    -0.07
    mat
    -0.07
    PCODE
    -0.07
    литель
    -0.07
     PA
    -0.07
     coward
    -0.07
    POSITIVE LOGITS
    archical
    0.06
     enact
    0.06
     partnerships
    0.05
    .optim
    0.05
    .addRow
    0.05
     parad
    0.05
    ｱ
    0.05
    //--------------------------------------------------------------↵
    0.05
    とも
    0.05
     frivol
    0.05
    Activations Density 0.002%

    No Known Activations