© 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. 126376
    Prev
    Next
    INDEX
    Explanations

    plasmid DNA

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of recombinant plasmid vector identifiers (e.g. “pcDNA3.1” and similar construct names).

    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
    131
    -0.07
     opc
    -0.07
    Operators
    -0.06
    120
    -0.06
     Reaper
    -0.06
    _NOP
    -0.06
    ectors
    -0.06
    .RESET
    -0.06
    _COMPILER
    -0.06
    іст
    -0.06
    POSITIVE LOGITS
    getElement
    0.07
    "]=$
    0.07
    睡
    0.06
     ayır
    0.06
     давно
    0.06
     %+
    0.06
     第二
    0.06
     Weiter
    0.06
     hiểm
    0.06
    ...</
    0.06
    Activations Density 0.003%

    No Known Activations