© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 85734
    Prev
    Next
    INDEX
    Explanations

    you are

    np_max-act · gemini-2.0-flash

    references to compiling and building software across different architectures.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron lights up on personal pronouns and common contractions (e.g. “I,” “you,” “I’m,” “it’s”), marking casual, conversational function words.

    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
    (Encoding
    -0.07
    ओ
    -0.07
    (Const
    -0.07
    ckill
    -0.07
    sch
    -0.07
     crowdfunding
    -0.06
     Soc
    -0.06
    common
    -0.06
     prime
    -0.06
    228
    -0.06
    POSITIVE LOGITS
    .desc
    0.06
     ALL
    0.06
    .Device
    0.06
     σαν
    0.06
     adb
    0.06
    복
    0.06
     OSX
    0.06
    411
    0.06
    �
    0.06
    levard
    0.06
    Activations Density 0.029%

    No Known Activations