© 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. 91613
    Prev
    Next
    INDEX
    Explanations

    gene

    np_max-act · gemini-2.0-flash

    genes involved in biosynthesis and metabolic pathways.

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

    This neuron selectively activates on technical terms and phrases related to genome or transcriptome analysis (e.g. sequences, genes, annotation, pathways, clusters).

    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
    .market
    -0.07
    	buff
    -0.06
     erotisk
    -0.06
    ้าก
    -0.06
    withdraw
    -0.06
     Desmond
    -0.06
    मर
    -0.06
     Rope
    -0.06
    BW
    -0.06
     Tig
    -0.06
    POSITIVE LOGITS
    ар
    0.07
     investor
    0.06
    :(
    0.06
    ��
    0.06
    ,__
    0.06
    _neurons
    0.06
    реб
    0.06
     affected
    0.06
    (iter
    0.06
    .querySelectorAll
    0.06
    Activations Density 0.011%

    No Known Activations