© 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. 110100
    Prev
    Next
    INDEX
    Explanations

    Code/file information

    np_max-act · gemini-2.0-flash

    The neuron responds to long sequences of hexadecimal characters (e.g. cryptographic checksums or hash strings).

    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
     tacos
    -0.06
     přij
    -0.06
     soll
    -0.06
     ظ
    -0.06
    tı
    -0.06
    三三
    -0.06
     زنده
    -0.06
    .liferay
    -0.06
     welche
    -0.06
     elementType
    -0.06
    POSITIVE LOGITS
    下的
    0.07
    ltk
    0.07
    حية
    0.06
     consistent
    0.06
     Developed
    0.06
     erectile
    0.06
    密
    0.06
     calm
    0.06
     defines
    0.06
     Rover
    0.06
    Activations Density 0.006%

    No Known Activations