© 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. 5835
    Prev
    Next
    INDEX
    Explanations

    keywords

    np_max-act · gemini-2.0-flash

    keywords related to political discussions and global security issues.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects mentions of extracting or highlighting important keywords or key phrases from a text.

    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
    .secret
    -0.07
     Criteria
    -0.06
     GLuint
    -0.06
     بعد
    -0.06
     Ways
    -0.06
    当前
    -0.06
    "class
    -0.06
     hom
    -0.06
     於
    -0.06
    (loader
    -0.06
    POSITIVE LOGITS
    豊
    0.07
     whether
    0.06
     εμφ
    0.06
    Deadline
    0.06
     Eş
    0.06
    ilingual
    0.06
     fisheries
    0.06
     shredded
    0.06
     Tues
    0.06
     fuller
    0.06
    Activations Density 0.013%

    No Known Activations