© 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. 128646
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    This neuron activates on Python code snippets—especially “for”‐loop constructs and their associated syntax (e.g. indentation, code fences, keywords like for, in, break).

    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
    .Ref
    -0.07
     Logic
    -0.07
    Fred
    -0.07
    sigmoid
    -0.06
    \Dependency
    -0.06
    avigator
    -0.06
     whereabouts
    -0.06
    #ga
    -0.06
    PerPixel
    -0.06
    うん
    -0.06
    POSITIVE LOGITS
     arrange
    0.07
     основных
    0.07
     crc
    0.06
     ith
    0.06
     prevailed
    0.06
    ，每
    0.06
    chten
    0.06
    遍
    0.06
    issance
    0.06
     pickle
    0.06
    Activations Density 0.023%

    No Known Activations