© 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 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. 57054
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash

    This neuron responds to advisory language—words and phrases used to suggest seeking help or guidance (e.g. “consult,” “assistance,” “advice,” “evaluation”).

    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
     kadar
    -0.06
    áo
    -0.06
     одной
    -0.06
     Değ
    -0.06
    _Server
    -0.06
    .fill
    -0.06
     正
    -0.06
     Chính
    -0.06
     inexperienced
    -0.06
     رنگ
    -0.06
    POSITIVE LOGITS
     Find
    0.07
    #get
    0.07
     reliance
    0.06
     DIG
    0.06
     retrieving
    0.06
     Щ
    0.06
     Ih
    0.06
    Г
    0.06
    ?“↵↵
    0.06
    gers
    0.06
    Activations Density 0.014%

    No Known Activations