© 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. 91258
    Prev
    Next
    INDEX
    Explanations

    URL redirects and web access

    np_max-act · gemini-2.0-flash

    The neuron activates on URLs and domain‐style tokens (e.g. “http”, “://”, “.com” and hostnames).

    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
     gấp
    -0.08
    眾
    -0.06
    有效
    -0.06
    Creative
    -0.06
     sponge
    -0.06
    PointXYZ
    -0.06
     NC
    -0.06
     všechny
    -0.06
    atatype
    -0.06
     Sponge
    -0.06
    POSITIVE LOGITS
    Wh
    0.08
     overt
    0.07
    -j
    0.07
    _ste
    0.06
    рощ
    0.06
    らの
    0.06
    ’app
    0.06
     이
    0.06
     ज
    0.06
    éo
    0.06
    Activations Density 0.015%

    No Known Activations