© 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. 91296
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    The neuron is highly responsive to tokens representing fractional numeric values (i.e. rationals like “2/7,” “1/11,” etc.).

    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
     upheld
    -0.06
     mãe
    -0.06
    inda
    -0.06
    lvl
    -0.06
    agh
    -0.06
    .E
    -0.06
     automate
    -0.06
    лены
    -0.06
    Score
    -0.06
     modelo
    -0.06
    POSITIVE LOGITS
     Zion
    0.07
    (iOS
    0.06
     投稿日
    0.06
    πέ
    0.06
    ¸
    0.06
    이야
    0.06
    \S
    0.06
     สาข
    0.06
    이가
    0.06
     tinha
    0.06
    Activations Density 0.015%

    No Known Activations