© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 41280
    Prev
    Next
    INDEX
    Explanations

    molecules and chemical compounds

    np_max-act · gemini-2.0-flash

    information related to the synthesis and behavior of amphiphilic molecules, particularly in the context of nanostructures and self-assembly processes.

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

    The neuron specializes in spotting mentions of amphiphilic molecules or surfactant compounds.

    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
    -Control
    -0.07
    nodes
    -0.07
    Targets
    -0.07
    _SET
    -0.06
    वत
    -0.06
    SPARENT
    -0.06
    -yellow
    -0.06
    esiz
    -0.06
     psi
    -0.06
     ns
    -0.06
    POSITIVE LOGITS
     mnoho
    0.06
     andra
    0.06
     UIG
    0.06
    _tF
    0.06
     Georg
    0.06
     Burr
    0.06
     vowed
    0.06
     McA
    0.06
     DateFormatter
    0.06
    _dma
    0.06
    Activations Density 0.025%

    No Known Activations