© 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. 13634
    Prev
    Next
    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash

    The neuron responds to common English prepositions (like “to,” “in,” and “with”).

    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
     варі
    -0.07
    -placement
    -0.06
     εφαρ
    -0.06
     ardından
    -0.06
    ตอน
    -0.06
     mereka
    -0.06
     �
    -0.06
     got
    -0.06
     ارائه
    -0.06
    (GTK
    -0.06
    POSITIVE LOGITS
    ipur
    0.08
     Cam
    0.07
     irrig
    0.07
     दर
    0.07
    unts
    0.07
    zhou
    0.07
    ensem
    0.06
     Irving
    0.06
     Billboard
    0.06
    >User
    0.06
    Activations Density 0.150%

    No Known Activations