© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 29584
    Prev
    Next
    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash

    Explanation for neuron 4: it does not activate on any regular text tokens and appears to be effectively “dead,” i.e. it does not detect any particular linguistic feature.

    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
     �
    -0.07
    ekil
    -0.07
    λεύ
    -0.06
    Stripe
    -0.06
    inth
    -0.06
    чи
    -0.06
    �
    -0.06
    狗
    -0.06
    طح
    -0.06
     mối
    -0.06
    POSITIVE LOGITS
     sped
    0.07
    يكا
    0.07
     Students
    0.07
     filled
    0.06
    /from
    0.06
     Depth
    0.06
     انقلاب
    0.06
    _now
    0.06
    利
    0.06
    決定
    0.06
    Activations Density 0.435%

    No Known Activations