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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 57703
    Prev
    Next
    INDEX
    Explanations

    genetics

    np_max-act · gemini-2.0-flash

    This neuron detects numeric components of genetic variant or polymorphism identifiers (e.g. the digit sequences in SNP or allele 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
    	handle
    -0.08
     університет
    -0.07
    ораль
    -0.06
     Ф
    -0.06
     WEEK
    -0.06
    dc
    -0.06
     df
    -0.06
    	pstmt
    -0.06
     Cow
    -0.06
     CM
    -0.06
    POSITIVE LOGITS
     Bahrain
    0.08
    JKLM
    0.07
    必
    0.07
    _generated
    0.07
    ++;
↵
    0.06
     Harm
    0.06
    娱乐
    0.06
    				
↵
    0.06
     nameLabel
    0.06
    -navbar
    0.06
    Activations Density 0.013%

    No Known Activations