© 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. 29573
    Prev
    Next
    INDEX
    Explanations

    Image tags

    np_max-act · gemini-2.0-flash

    The neuron activates on image‐embedding markup (e.g. `<img>` tags and `src` attributes pointing to `.png`/.jpg` files).

    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
    fps
    -0.08
    mongodb
    -0.06
    .news
    -0.06
     getline
    -0.06
     uninstall
    -0.06
     az
    -0.06
    _dept
    -0.06
     forgotten
    -0.06
     Receiver
    -0.06
    ystems
    -0.06
    POSITIVE LOGITS
     Parm
    0.07
    rač
    0.07
     alternating
    0.06
     Yayın
    0.06
     SDLK
    0.06
    �
    0.06
     ted
    0.06
     propor
    0.06
    usually
    0.06
    isbury
    0.06
    Activations Density 0.013%

    No Known Activations