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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 738
    Prev
    Next
    INDEX
    Explanations

    ular

    np_max-act · gemini-2.0-flash

    The neuron activates on words containing the suffix “­ular,” i.e. tokens ending in “ular.”

    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
    ーティ
    -0.07
     Bazı
    -0.07
     btc
    -0.07
    reece
    -0.07
    oxetine
    -0.06
     sexdate
    -0.06
    scaling
    -0.06
     Sex
    -0.06
    'es
    -0.06
    xde
    -0.06
    POSITIVE LOGITS
    ar
    0.11
    ular
    0.11
    AR
    0.10
    alar
    0.10
    ER
    0.09
    ars
    0.09
    ар
    0.09
    arr
    0.09
    er
    0.08
    ilar
    0.08
    Activations Density 0.015%

    No Known Activations