© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 85824
    Prev
    Next
    INDEX
    Explanations

    Vulgar slang

    np_max-act · gemini-2.0-flash

    sentences with informal conversational patterns, particularly in questions and exclamations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @chuloivawork

    the beginnings of sentences (sentence-initial tokens, often capitalized or after punctuation).

    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_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
    quette
    -0.07
     skull
    -0.07
     scooter
    -0.07
     stunning
    -0.07
    لان
    -0.06
     invokes
    -0.06
     succeeding
    -0.06
     chick
    -0.06
     played
    -0.06
     feelings
    -0.06
    POSITIVE LOGITS
    _passwd
    0.07
     ülkenin
    0.07
    .UIManager
    0.07
     AccessToken
    0.07
    .OrderByDescending
    0.06
    吸
    0.06
    ूछ
    0.06
     科
    0.06
    .addMouseListener
    0.06
    ():
↵
    0.06
    Activations Density 0.273%

    No Known Activations