© 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. 126742
    Prev
    Next
    INDEX
    Explanations

    Bean

    np_max-act · gemini-2.0-flash

    The neuron flags tokens related to Spring framework bean definitions and configuration (e.g. “@Configuration,” “@Enable…,” “Bean,” “FactoryBean,” property names like “driverClassName,” 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
    Americ
    -0.06
    assandra
    -0.06
    (++
    -0.06
    }[
    -0.06
    (xx
    -0.06
     ABD
    -0.06
     ROT
    -0.06
     sled
    -0.06
    GetString
    -0.06
    Uid
    -0.06
    POSITIVE LOGITS
     purposes
    0.07
    utive
    0.07
    stream
    0.07
    _waiting
    0.07
     +**************
    0.06
    skip
    0.06
    .AddListener
    0.06
    itious
    0.06
    .Directory
    0.06
    ừa
    0.06
    Activations Density 0.078%

    No Known Activations