© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 124661
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    This neuron does not respond to any tokens in these samples.

    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
     trapped
    -0.07
     bleak
    -0.07
     MISSING
    -0.07
     Shed
    -0.06
     masculinity
    -0.06
    .management
    -0.06
    669
    -0.06
     Pain
    -0.06
     logistic
    -0.06
    prestashop
    -0.06
    POSITIVE LOGITS
    =response
    0.06
     tisíc
    0.06
    _e
    0.06
    aryawan
    0.06
     г
    0.06
     πως
    0.06
     价格
    0.06
     spel
    0.05
    ，如
    0.05
    ussion
    0.05
    Activations Density 0.156%

    No Known Activations