© 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. 91612
    Prev
    Next
    INDEX
    Explanations

    genetics and bioethics

    np_max-act · gemini-2.0-flash

    The neuron activates on terms related to gene-editing (e.g. “gene,” “editing,” “CRISPR,” “genome”) and thus flags discussion of genome-editing technologies and their ethical implications.

    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
     �
    -0.06
     GPL
    -0.06
    .throw
    -0.06
     Sitting
    -0.06
     анализ
    -0.06
     Comfort
    -0.06
     Architecture
    -0.06
    idine
    -0.06
    .eng
    -0.06
     encyclopedia
    -0.06
    POSITIVE LOGITS
    -condition
    0.07
     Charg
    0.07
    anı
    0.06
     searcher
    0.06
    _already
    0.06
    али
    0.06
     inne
    0.06
     uc
    0.06
    ὸ
    0.06
    resents
    0.06
    Activations Density 0.017%

    No Known Activations