© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 109285
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on instances of the definite article “the.”

    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
     focuses
    -0.07
     partic
    -0.06
    頁
    -0.06
    饮
    -0.06
    	users
    -0.06
    vided
    -0.06
     seated
    -0.05
     indicate
    -0.05
    sans
    -0.05
     стан
    -0.05
    POSITIVE LOGITS
    .AL
    0.07
     повинен
    0.07
     περιοχή
    0.07
    )i
    0.07
    _NOTICE
    0.07
     incontri
    0.07
     polov
    0.07
    (po
    0.07
     goalie
    0.07
     ComVisible
    0.07
    Activations Density 0.010%

    No Known Activations