© 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. 41221
    Prev
    Next
    INDEX
    Explanations

    Enneagrams

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the term “Enneagram” (as in “Enneagram Type …”).

    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
    etě
    -0.06
    τσι
    -0.06
    宁
    -0.06
     qint
    -0.06
    Keyboard
    -0.06
     Chung
    -0.06
     pooling
    -0.06
    ヴ
    -0.06
     coil
    -0.06
     cabin
    -0.06
    POSITIVE LOGITS
    ázi
    0.07
    lich
    0.06
    .MediaType
    0.06
    USA
    0.06
     j
    0.06
     armed
    0.06
    IDEO
    0.06
     electrons
    0.06
     honoring
    0.06
     slang
    0.06
    Activations Density 0.001%

    No Known Activations