© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 41505
    Prev
    Next
    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash

    This neuron responds to tokens involved in conditional comparison expressions (e.g. `==`, `<=`) in code.

    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
     Scandin
    -0.06
     Rum
    -0.06
     Chapters
    -0.06
    確認
    -0.06
     Static
    -0.06
     групп
    -0.06
    <"
    -0.06
     NYC
    -0.06
    Ap
    -0.06
     STATIC
    -0.06
    POSITIVE LOGITS
    „A
    0.07
    .student
    0.06
    }↵↵↵
    0.06
     fatalError
    0.06
    .super
    0.06
    /QĐ
    0.06
    艇
    0.06
    ]==
    0.06
     temiz
    0.06
     ebx
    0.06
    Activations Density 0.012%

    No Known Activations