© 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. 30101
    Prev
    Next
    INDEX
    Explanations

    Chromosome pairs

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of chromosomal karyotypes or numeric chromosome-count notations (e.g. “46,XX,” “47,XXY,” “monosomy,” “trisomy”).

    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
    -bold
    -0.07
     그는
    -0.07
    dae
    -0.06
     kèm
    -0.06
    ####
    -0.06
     Besch
    -0.06
     Gos
    -0.06
     peč
    -0.06
    sequ
    -0.06
    ammed
    -0.06
    POSITIVE LOGITS
    [list
    0.07
    	ORDER
    0.07
     assumed
    0.07
     mpl
    0.06
    .SQLite
    0.06
    NOWLED
    0.06
     všem
    0.06
     covers
    0.06
    ")+
    0.06
     autres
    0.06
    Activations Density 0.002%

    No Known Activations