© 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. 89216
    Prev
    Next
    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash

    The neuron activates on template‐style directive delimiters and special comment tags (e.g. `<%`, `%>`, `<!--`, `-->`, `#`), i.e. markers that begin or end embedded code or directives.

    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
    ToDevice
    -0.07
    ト
    -0.07
     Barcelona
    -0.07
     ▼
    -0.07
     esto
    -0.07
    �
    -0.07
    ..↵↵↵↵
    -0.06
    ох
    -0.06
    ์ของ
    -0.06
     женщины
    -0.06
    POSITIVE LOGITS
    CGPoint
    0.06
    .opt
    0.06
    .openapi
    0.06
    袋
    0.06
    fait
    0.06
    _wait
    0.06
    -layer
    0.06
    velocity
    0.06
     setType
    0.05
     skimage
    0.05
    Activations Density 0.012%

    No Known Activations