© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 92184
    Prev
    Next
    INDEX
    Explanations

    ($

    np_max-act · gemini-2.0-flash

    The neuron fires on PHP variable‐array access expressions—i.e. dollar‐sign variables being indexed (e.g. `$pages[0]`, `$_GET[‘pinned’]`, etc.).

    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
    _simple
    -0.07
    Activate
    -0.06
    Human
    -0.06
    ittle
    -0.06
    ,alpha
    -0.06
    /api
    -0.06
     Put
    -0.06
    pygame
    -0.06
    otts
    -0.06
    chapter
    -0.06
    POSITIVE LOGITS
     отли
    0.07
     mlad
    0.06
     taxa
    0.06
    (mouse
    0.06
     inters
    0.06
     vern
    0.06
    579
    0.06
    (MouseEvent
    0.06
     mars
    0.06
     odmít
    0.06
    Activations Density 0.007%

    No Known Activations