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

    Neuronpedia

    Jacobian LensNEW
    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. 57489
    Prev
    Next
    INDEX
    Explanations

    Wort

    np_max-act · gemini-2.0-flash

    The neuron fires on the names of herbal remedies or supplements.

    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
    _hero
    -0.07
    ibles
    -0.07
     diferente
    -0.07
    ibili
    -0.07
    -Control
    -0.07
    -shot
    -0.07
     segunda
    -0.07
     laptop
    -0.06
    ader
    -0.06
    _stride
    -0.06
    POSITIVE LOGITS
     incumbent
    0.07
     thuê
    0.06
     lộ
    0.06
     شف
    0.06
    _CHARACTER
    0.06
     광
    0.06
    Diagnostic
    0.05
    /archive
    0.05
     Комп
    0.05
     Kub
    0.05
    Activations Density 0.000%

    No Known Activations