© 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. 7566
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    This neuron detects checks for parent‐directory traversal (i.e. the “..” in paths).

    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
    acobian
    -0.08
    /locale
    -0.07
     Georges
    -0.07
     xs
    -0.06
     donating
    -0.06
     nullable
    -0.06
     Ellison
    -0.06
     особ
    -0.06
    alling
    -0.06
     isolation
    -0.06
    POSITIVE LOGITS
     Mathematical
    0.07
     karıştır
    0.07
     Massachusetts
    0.07
    ุญาต
    0.06
    ############################
    0.06
    Represent
    0.06
     Pitt
    0.06
    backgroundColor
    0.06
    戰
    0.06
    ======↵
    0.06
    Activations Density 0.062%

    No Known Activations