© 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. 55824
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    This neuron responds to numeric in‐text citation or reference markers.

    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
    defs
    -0.06
     nonlinear
    -0.06
     unavailable
    -0.06
    pirit
    -0.06
     黑
    -0.06
     Uma
    -0.06
     gateway
    -0.06
     Blanco
    -0.05
    .Serve
    -0.05
     battlefield
    -0.05
    POSITIVE LOGITS
     Bourbon
    0.08
    _CC
    0.07
     gün
    0.07
    NC
    0.07
    .prepareStatement
    0.07
     hygiene
    0.07
     JSName
    0.07
    *******/↵
    0.07
     نفت
    0.07
    .ts
    0.07
    Activations Density 0.024%

    No Known Activations