© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 58076
    Prev
    Next
    INDEX
    Explanations

    posts

    np_max-act · gemini-2.0-flash

    This neuron fires on forum post metadata lines (e.g. “Joined:”, “Posts:”, “Location:”, “Post subject:”, “Posted:”).

    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
    _sentence
    -0.07
     вік
    -0.07
    IsRequired
    -0.06
    董
    -0.06
     conditioning
    -0.06
    MenuItem
    -0.06
    ChildIndex
    -0.06
    浦
    -0.06
    OGLE
    -0.06
    essed
    -0.06
    POSITIVE LOGITS
     كام
    0.07
     shim
    0.06
    輝
    0.06
     Hay
    0.06
    Hay
    0.06
     Gins
    0.06
     Gamma
    0.06
    GO
    0.06
     Useful
    0.06
     IMM
    0.06
    Activations Density 0.003%

    No Known Activations