© 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 EvalsExportsAPI 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. 38794
    Prev
    Next
    INDEX
    Explanations

    genes and cell cycle

    np_max-act · gemini-2.0-flash

    This neuron responds to mentions of specific cell-cycle inhibitor proteins, especially CDK inhibitor names like p15INK4B, p16INK4A, and p21WAF1/CIP1.

    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
     Dou
    -0.07
     Λ
    -0.06
     Pages
    -0.06
    	BOOST
    -0.06
    _residual
    -0.06
     〈
    -0.06
    )r
    -0.06
    -other
    -0.06
     आवश
    -0.06
     filament
    -0.06
    POSITIVE LOGITS
    :url
    0.07
    ben
    0.07
    τυ
    0.06
    .Scroll
    0.06
    .cp
    0.06
     Times
    0.06
     close
    0.06
    ban
    0.06
     muzzle
    0.06
    قل
    0.06
    Activations Density 0.001%

    No Known Activations