© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 43298
    Prev
    Next
    INDEX
    Explanations

    flower

    np_max-act · gemini-2.0-flash

    The neuron activates on words signaling a flower blooming (e.g. “bloom,” “flower”).

    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
     models
    -0.07
     interpretation
    -0.07
     polymer
    -0.06
    وزه
    -0.06
    BYTES
    -0.06
     micro
    -0.06
    -largest
    -0.06
     systems
    -0.06
     schizophren
    -0.06
     disdain
    -0.06
    POSITIVE LOGITS
     olmadığı
    0.07
    ">@
    0.07
    ––
    0.06
    iếng
    0.06
    анка
    0.06
     roleName
    0.06
     idiots
    0.06
    @register
    0.06
    @Entity
    0.06
    /table
    0.06
    Activations Density 0.306%

    No Known Activations