© 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. 15-RESID-POST-AA
    11. 2221
    Prev
    Next
    INDEX
    Explanations

    height

    np_max-act · gemini-2.0-flash

    It detects numeric tokens (numbers and decimal numeric values), especially CSS measurement values and other numeric literals in code.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    นาน
    -0.06
     나가
    -0.06
     tão
    -0.06
    ван
    -0.06
     z
    -0.06
    �
    -0.06
    丘
    -0.06
    279
    -0.06
    ันอ
    -0.06
    -phase
    -0.06
    POSITIVE LOGITS
     ->
    0.07
    ’nın
    0.07
    ographics
    0.06
     сейчас
    0.06
    前往
    0.06
    <img
    0.06
    _NEXT
    0.06
    ическая
    0.06
     Chief
    0.06
    ，在
    0.06
    Activations Density 0.006%

    No Known Activations